{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 603, "referenced_widgets": [ "5c4cf45e5bcd4f3ab86dd5ee6014702f", "615592a5e55e43b7b5c4b6003df3f4a4", "ce819f97526148dd868d7865e0050250", "bf91e8d2b3d54934a1b792847d1b60d7", "0f27fa287db245558b8b5a472724a4dc", "b37183a361974bc4952ccdd8b5feba77", "ff90238949574f7b99fbf78d03502a4b", "0b489d8cabe84ea8822fbbe69ddea6ec", "43e2323030e34f46856104d3912a7357", "f3ae9638777040f4b464a3ff4e20350f", "4f1bcfb138cc4987ad43f6144378344b", "56d3f120efba43ab9d6691906d07a2f1", "cff6d60f51374e0e9dec98ff9a3bea08", "fd31b26fba6e403b8d3167c077eade6c", "99d71706a23b4241a5b7e073e745f791", "506c02e216be4252923ebf4bff9bfb3f", "73c071d37f384a698fd32b7de32762f9", "3b4d094f37284fa2bc736a67b817e454", "2580b4e469ea44149026417447c0bf77", "4284d348209d4ce3a6f7ad0ce6d411a3", "2234569c0aec4ed7a97fe9348b1c5f33", "d6e72b9158874e64ad54bb00262d505d", "17403e85452c4c1fb7166185857e0883", "5e7a5e1f12c64d878133502901e5bd3c", "d2ff54ec49174c51b34170a09ab9d710", "5c36b42f495e46e2a3327b6c48580e37", "5d332903ab6d45a0a9255ac320d6ddb1", "ae73faebc89b4c24888893921aedc29c", "70286b77c3554df9b01946c85356b940", "d0a5cc16a8f64458979923e8664ebcf5", "25269e443c904728bffd7c7fe1ceb1f6", "337c412fa8ae4749a380f2eeb1ac241f", "04eed28ede0544b3acd1709129e63ea4", "57ff204a78df4d39a33c7a7f0822bb55", "6ec4cf9385b74541abbb639bddcf04d8", "5a7cb1594b264fe38f35f2dacc7fb480", "740aadf9626d4521a213c531ef95a8e3", "ec4bd2e7a974404f98fcaf23971e23fc", "a2e92ed58d994ebc871b605206fbf49f", "ccdd3a92abc746c2a845e3aa5e0718a5", "32d84fff85134a1db868626f42d5f33c", "9f0ea766f5e746c083e7af4d7c4a65dc", "541d7d11e9bb43b1a4e1dc2d0454e25a", "34ed2cddfbb74516ad9f75652424cde2", "0e20fb6770524e0c8f8327ea89158da2", "5ea362f87e9a49d1a4595135ed737131", "e7b80bc1e692486187e85f2af7bbf766", "b41b615e3db04d95a375c8675ac98f5e", "e09c9da093834cd588c582dbe3d834b3", "df18300b8fe543faa3905032c24d7265", "f3ec43a01b5a4d258d3d27a8196af437", "98094a2c7de84ff8b29dd56e88f646ae", "4f57d6f9e21f4699becdbdb8e5c2cf01", "fbaf2d5e764c4cfdaeeb1ad0594c1bb4", "e06ef7766d644508acc14baf4cfb2272", "b0707545040c439f9da77d20abae7439", "bcd8dac75a1f45dfa8e40c09e0c4aabb", "3fd4646511914c6c85c6def63397c803", "2f873b479d88453b95cb013de7f766be", "60e3c762040e45bd91e35b5626571f74", "a0f325a33cef4b7fb4fe1bf0352a44c3", "f98630edbd6c4f08b33958e9322abc40", "f6add67852044c4fb0f51673be16b893", "b3287fb39e9a4ae2b6a9a9d542c4294d", "b06c56d1a2284119b7f8005db1ba984f", "232a527afd0b443ca962416ee954cd6f", "766cb257f49c4125aa0ced85df2e7f8c", "22633b763909428f82953a07a87d78b8", "4e0551b2d62c478e99c9483137e5e7ba", "ea3c74099bca426989afa332b2e660d3", "277b7fcf492f461b922767b425ddfd51", "52b0deb295e94dda85d73594744d523b", "3e10bfba6a644484a64f4c033d8715c2", "48f8f7cda86944f39476ba97dc376bd1", "07e379cb99154b728443c08f821303c5", "6c22c9a2bbbc4dd4aef35334ba02bda3", "c45d64c50342423fb7df622d7e37e7e6", "980261fb60494e499b6c012c359576e1", "4890ed78674f4b03a5f6e4356dc7311f", "95852c7235524df6baae36d4937e67ed", "e47a8fc89049437182f2f453c15b105d", "3e6eee01b06742c1a8485617625fe137", "8d4bc08f060c4139a07c76b2e1c33fb2", "6d6ecd7462464623b1e218678a19e379", "7c70f5fd11954f49a25bfb5ebd2e29b0", "7134af62dd5044ab8335531c83330219", "bb7363e8e32142548f419f8a67d529e8", "9b925356804d467ea3d802f804067ad5", "e141541d78ff422687947fc5cacb2bea", "b6b11430259347a58075d298f397903a", "72d501ddf0f94e6bb274f6956af2be07", "25ae9804eb0c4cc2b3f4c5c4220cf89d", "329ac9f854cb451f99a63332c7273350", "270d337be1104b15be947dacb3d1fca4", "6d78ad3adac749e69c928b3a90567ba6", "e9c47a8513814bf0be84ba7897dfd261", "96b042bd9efe4120ab2fd378fd4a36e7", "e00cfe826fd04b1f866e9aadc98d8c93", "d28b9fc961494d9b9be6486355d9ece7", "6a7d6ab9863c48c099454bb73d53b61e", "322a4ac26c024fe287f6215738b5b2da", "05c53e525b1346f68c6434ab781b7629", "79434a3e6e70481ba1cbafccc5285ecb", "0e227bfaa33c46df980d47744e5ac3e6", "0403ae9fe7004e34a06cbce76d42b641", "154db1f768174f998292d6fd79fa2636", "2823d0fd91844f1daf7a5f51c6c9a972", "f7946476f3904b06be92936f54dedae8", "d86f568779fc4e53a6310d087393ccf2", "4d9943cb14b7450e97b41dc2f3f76709", "852e1eafe30944589d8353cc0774401b", "8c66db9882fa43feb3564275a0a144bb", "56b79f86e7b44c84bab417cb2e543270", "bcb73fefa76840f9a69a172fd7e78dd7", "c2d3603dab544ceeb0a8880526264396", "563f9674405b46348511cd4f401f9523", "66d3b102e0de4be0ad56cfdf514078db", "f7c6b573ba814329ad14e728627683e8", "3beb98c5640045a097f12b0cc50cdd36", "e6b6705e66934a03acd5c5fed825b2ff", "be84a30bc3aa4421897171ba4d321076", "28b2a527e8004669bfb48bb2ee9f206a", "fcc2195ce5d84f7080f8c3d47d1d2816", "bff98fe2e86d4ab0b66fa083ae74ce41", "a0a5de0898a64bf49bacb2db2c4b252e", "ce9a10d228724a3a9d70329b8fd7c47c", "576ba493cfe84f7dab73d166c2609c7b", "a7a56cd6c6234343a4da9a448acd94c7", "5f6b06d2611c40c59ab259f9b37d7fc7", "cf3ee86ef8e14f2d8b3991c61789f4e0", "fe48027a0bc94da7a9f200f2503bf48e", "afb2a13643ed451db7d880421d1e1bf7" ] }, "id": "hv3wo4SeAmAX", "outputId": "f6bcf0af-70be-4673-cb1a-225fe58eb640" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "2026-01-05 18:18:15.881627: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", "[xformers|WARNING]WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:\n", " PyTorch 2.8.0+cu128 with CUDA None (you have 2.8.0+cu128)\n", " Python 3.12.11 (you have 3.12.11)\n", " Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)\n", " Memory-efficient attention, SwiGLU, sparse and more won't be available.\n", " Set XFORMERS_MORE_DETAILS=1 for more details\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "========\n", "Switching to PyTorch attention since your Xformers is broken.\n", "========\n", "\n", "Unsloth: Xformers was not installed correctly.\n", "Please install xformers separately first.\n", "Then confirm if it's correctly installed by running:\n", "python -m xformers.info\n", "\n", "Longer error message:\n", "xFormers can't load C++/CUDA extensions. xFormers was built for:\n", " PyTorch 2.8.0+cu128 with CUDA None (you have 2.8.0+cu128)\n", " Python 3.12.11 (you have 3.12.11)\n", " Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)\n", " Memory-efficient attention, SwiGLU, sparse and more won't be available.\n", "🦥 Unsloth Zoo will now patch everything to make training faster!\n", "Unsloth: WARNING `trust_remote_code` is True.\n", "Are you certain you want to do remote code execution?\n", "==((====))== Unsloth 2025.11.4: Fast Qwen2_5_Vl patching. Transformers: 4.57.1.\n", " \\\\ /| NVIDIA GeForce RTX 3060. Num GPUs = 1. Max memory: 11.631 GB. Platform: Linux.\n", "O^O/ \\_/ \\ Torch: 2.8.0+cu128. CUDA: 8.6. CUDA Toolkit: 12.8. Triton: 3.4.0\n", "\\ / Bfloat16 = TRUE. FA [Xformers = None. FA2 = False]\n", " \"-____-\" Free license: http://github.com/unslothai/unsloth\n", "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n", "Unsloth: Qwen2_5_Vl does not support SDPA - switching to fast eager.\n" ] } ], "source": [ "import torch\n", "import json\n", "from unsloth import FastVisionModel\n", "from unsloth.trainer import UnslothVisionDataCollator\n", "from trl import SFTTrainer, SFTConfig\n", "# unsloth/Qwen2.5-VL-7B-Instruct-bnb-4bit\n", "model, tokenizer = FastVisionModel.from_pretrained(\n", " \"unsloth/Qwen2.5-VL-7B-Instruct-bnb-4bit\",\n", " load_in_4bit=True,\n", " use_gradient_checkpointing=\"unsloth\",\n", " trust_remote_code=True,\n", " max_seq_length=2048,\n", ")" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "instruction = (\n", " \"You are a medical vision-language model specialized in chest X-ray interpretation. \"\n", " \"Analyze the image STRICTLY based on visible radiographic evidence. \"\n", " \"Do NOT infer diagnoses from clinical history, labels, devices, or non-specific cues.\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"MANDATORY REASONING ORDER (NO EXCEPTIONS)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"Step 1: Describe ONLY what is visually assessed in the image.\\n\"\n", " \"Step 2: Identify which anatomical regions were examined and why.\\n\"\n", " \"Step 3: Explicitly state whether pulmonary edema, congestion, or pleural effusion \"\n", " \"is PRESENT or ABSENT based on visible evidence.\\n\"\n", " \"Step 4: Assign the disease label using ONLY Step 3.\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"CHF DIAGNOSTIC CRITERIA (STRICT)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"Congestive Heart Failure (CHF) may be diagnosed ONLY if at least ONE of the following \"\n", " \"is CLEARLY and DEFINITELY visible:\\n\\n\"\n", "\n", " \"✔ Interstitial pulmonary edema (e.g., definite Kerley B lines)\\n\"\n", " \"✔ Alveolar pulmonary edema\\n\"\n", " \"✔ Pulmonary vascular congestion WITH true cephalization\\n\"\n", " \"✔ Definite pleural effusion attributable to heart failure\\n\"\n", " \"✔ Perihilar haze WITH coexisting interstitial or alveolar edema\\n\\n\"\n", "\n", " \"------------------------------------------------\\n\"\n", " \"NOT SUFFICIENT FOR CHF (DO NOT USE):\\n\"\n", " \"------------------------------------------------\\n\"\n", "\n", " \"✘ Cardiomegaly alone\\n\"\n", " \"✘ Prominent vessels without cephalization\\n\"\n", " \"✘ Mild, diffuse, or vague haziness\\n\"\n", " \"✘ Patchy opacity without edema pattern\\n\"\n", " \"✘ Atelectasis or scarring alone\\n\"\n", " \"✘ Presence of medical devices\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"HARD NORMAL OVERRIDE (ABSOLUTE)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"If ALL of the following are true:\\n\"\n", " \"- Lung fields are clear or near-clear\\n\"\n", " \"- NO definite pulmonary edema\\n\"\n", " \"- NO interstitial markings (Kerley lines)\\n\"\n", " \"- NO pleural effusion\\n\\n\"\n", "\n", " \"THEN:\\n\"\n", " \"✔ Disease label MUST be: NORMAL\\n\"\n", " \"✔ CHF diagnosis is FORBIDDEN\\n\\n\"\n", "\n", " \"This rule OVERRIDES cardiomegaly, vascular prominence, \"\n", " \"projection issues, or limited inspiration.\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"UNCERTAINTY HANDLING (STRICT)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"If findings require speculative language such as:\\n\"\n", " \"\\\"possible\\\", \\\"suspected\\\", \\\"could represent\\\", \"\n", " \"\\\"cannot exclude\\\", \\\"questionable\\\", \\\"likely artifact\\\"\\n\\n\"\n", "\n", " \"THEN:\\n\"\n", " \"✔ Default to NORMAL\\n\"\n", " \"✔ Do NOT diagnose CHF\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"BOUNDING BOX RULES (CRITICAL)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"Bounding boxes are REQUIRED for BOTH NORMAL and CHF cases.\\n\\n\"\n", "\n", " \"Bounding boxes:\\n\"\n", " \"- Indicate regions that were visually assessed\\n\"\n", " \"- Show HOW reported findings were evaluated\\n\"\n", " \"- Do NOT imply presence or absence of disease\\n\\n\"\n", "\n", " \"Rules:\\n\"\n", " \"✔ Boxes MUST align with anatomical structures described in the report\\n\"\n", " \"✔ Boxes MUST correspond to evaluated regions \"\n", " \"(lungs, hila, costophrenic angles, heart)\\n\"\n", " \"✔ Normal cases MUST still include boxes over assessed normal structures\\n\"\n", " \"✘ Boxes must NOT be used to justify disease by themselves\\n\"\n", " \"✘ Do NOT place boxes on regions not discussed in the report\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"HALLUCINATION PREVENTION (ZERO TOLERANCE)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"- Do NOT invent edema, effusions, or interstitial markings\\n\"\n", " \"- Do NOT describe findings not clearly visible\\n\"\n", " \"- Do NOT upgrade equivocal findings to disease\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"OUTPUT FORMAT (EXACT)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"Disease: \\n\"\n", " \"Report: \\n\"\n", " \"BoundingBoxes: x1,y1,x2,y2 format>\"\n", ")\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Forced-train images (including augs): 16\n", "✅ Sanity check passed — no forbidden base IDs in test set\n", "Train: 2312\n", "Val: 288\n", "Test: 288\n", "Train samples: 2312\n", "Val samples: 288\n", "Test samples: 288\n" ] } ], "source": [ "import pandas as pd\n", "import ast\n", "import os\n", "from PIL import Image\n", "from sklearn.model_selection import train_test_split\n", "\n", "# --------------------------------------------------\n", "# CONFIG\n", "# --------------------------------------------------\n", "CSV_PATH = \"/home/shanin/Desktop/SHANIN/EyeGaze/CHEST/final_dataset.csv\"\n", "\n", "# Base image IDs (WITHOUT extension or _augX)\n", "FORBIDDEN_BASE_IDS = {\n", " \"1004bccd-c2a1dd49-608fd792-f1f1f173-ffec24f3\",\n", " \"6ba111a6-5a2d9336-005afd4a-46314a71-d647f4c9\",\n", " \"16344c71-8bd55bc8-952edb72-c361b4e8-c4980ee1\",\n", " \"c75c63ff-5099eac4-514044ea-c6878959-39ef4039\",\n", "}\n", "\n", "# --------------------------------------------------\n", "# LOAD & PREPROCESS\n", "# --------------------------------------------------\n", "df = pd.read_csv(CSV_PATH)\n", "\n", "# Remove pneumonia\n", "df = df[df[\"disease\"] != \"pneumonia\"]\n", "\n", "# Shuffle\n", "df = df.sample(frac=1, random_state=42).reset_index(drop=True)\n", "\n", "# Extract filename\n", "df[\"image_name\"] = df[\"image_path\"].apply(os.path.basename)\n", "\n", "# Extract base ID (remove .png and _augX)\n", "def extract_base_id(filename):\n", " name = filename.replace(\".png\", \"\")\n", " if \"_aug\" in name:\n", " name = name.split(\"_aug\")[0]\n", " return name\n", "\n", "df[\"base_id\"] = df[\"image_name\"].apply(extract_base_id)\n", "\n", "# --------------------------------------------------\n", "# SEPARATE FORCED TRAIN IMAGES\n", "# --------------------------------------------------\n", "df_forced_train = df[df[\"base_id\"].isin(FORBIDDEN_BASE_IDS)]\n", "df_no_test = df[~df[\"base_id\"].isin(FORBIDDEN_BASE_IDS)]\n", "\n", "print(f\"Forced-train images (including augs): {len(df_forced_train)}\")\n", "\n", "# --------------------------------------------------\n", "# STRATIFIED SPLITS\n", "# --------------------------------------------------\n", "# 10% test\n", "train_val_df, test_df = train_test_split(\n", " df_no_test,\n", " test_size=0.1,\n", " stratify=df_no_test[\"disease\"],\n", " random_state=42\n", ")\n", "\n", "# ~10% val\n", "train_df, val_df = train_test_split(\n", " train_val_df,\n", " test_size=0.1111,\n", " stratify=train_val_df[\"disease\"],\n", " random_state=42\n", ")\n", "\n", "# Force forbidden images into TRAIN\n", "train_df = pd.concat([train_df, df_forced_train], ignore_index=True)\n", "\n", "# --------------------------------------------------\n", "# SANITY CHECK\n", "# --------------------------------------------------\n", "assert FORBIDDEN_BASE_IDS.isdisjoint(set(test_df[\"base_id\"])), \\\n", " \"❌ ERROR: Forbidden (or augmented) images found in TEST set!\"\n", "\n", "print(\"✅ Sanity check passed — no forbidden base IDs in test set\")\n", "\n", "print(\"Train:\", len(train_df))\n", "print(\"Val:\", len(val_df))\n", "print(\"Test:\", len(test_df))\n", "\n", "# --------------------------------------------------\n", "# BOX CONVERSION\n", "# --------------------------------------------------\n", "def convert_boxes_to_qwen_format(boxes_str):\n", " try:\n", " boxes_list = ast.literal_eval(boxes_str)\n", " if not boxes_list:\n", " return \"\"\n", "\n", " best_box = max(\n", " boxes_list,\n", " key=lambda b: b.get(\"confidence\", 0) if isinstance(b, dict) else 0\n", " )\n", "\n", " if isinstance(best_box, dict):\n", " x1, y1, x2, y2 = best_box[\"x1\"], best_box[\"y1\"], best_box[\"x2\"], best_box[\"y2\"]\n", " else:\n", " x1, y1, x2, y2 = best_box[:4]\n", "\n", " return f\"{x1},{y1},{x2},{y2}\"\n", "\n", " except Exception as e:\n", " print(f\"Box parse error: {e}\")\n", " return \"\"\n", "\n", "def create_sample(row):\n", " if not os.path.exists(row[\"image_path\"]):\n", " raise FileNotFoundError(row[\"image_path\"])\n", "\n", " image = Image.open(row[\"image_path\"]).convert(\"RGB\")\n", " boxes_text = convert_boxes_to_qwen_format(row[\"heatmap_rescaled_boxes\"])\n", "\n", " return {\n", " \"messages\": [\n", " {\n", " \"role\": \"user\",\n", " \"content\": [\n", " {\"type\": \"text\", \"text\": instruction},\n", " {\"type\": \"image\", \"image\": image},\n", " ],\n", " },\n", " {\n", " \"role\": \"assistant\",\n", " \"content\": [\n", " {\n", " \"type\": \"text\",\n", " \"text\": (\n", " f\"Disease: {row['disease']}\\n\"\n", " f\"Report: {row['radiology_report']}\\n\"\n", " f\"BoundingBoxes: {boxes_text}\"\n", " ),\n", " }\n", " ],\n", " },\n", " ]\n", " }\n", "\n", "# --------------------------------------------------\n", "# BUILD DATASETS\n", "# --------------------------------------------------\n", "def build_dataset(split_df, name):\n", " dataset = []\n", " for idx, row in split_df.iterrows():\n", " try:\n", " dataset.append(create_sample(row))\n", " except Exception as e:\n", " print(f\"[{name}] Skipping row {idx}: {e}\")\n", "\n", " print(f\"{name} samples: {len(dataset)}\")\n", " return dataset\n", "\n", "train_set = build_dataset(train_df, \"Train\")\n", "val_set = build_dataset(val_df, \"Val\")\n", "test_set = build_dataset(test_df, \"Test\")\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Train: 2310\n", "Val: 289\n", "Test: 289\n", "Train samples: 2310\n", "Val samples: 289\n", "Test samples: 289\n" ] } ], "source": [ "# import pandas as pd\n", "# import ast\n", "# import os\n", "# from PIL import Image\n", "# from sklearn.model_selection import train_test_split\n", "\n", "# df = pd.read_csv(\"/home/shanin/Desktop/SHANIN/EyeGaze/CHEST/final_dataset.csv\")\n", "# # Remove pneumonia\n", "# df = df[df[\"disease\"] != \"pneumonia\"]\n", "# # Shuffle\n", "# df = df.sample(frac=1, random_state=42).reset_index(drop=True)\n", "\n", "# # 10% test\n", "# train_val_df, test_df = train_test_split(\n", "# df,\n", "# test_size=0.1,\n", "# stratify=df[\"disease\"],\n", "# random_state=42\n", "# )\n", "\n", "# # ~10% val (of total)\n", "# train_df, val_df = train_test_split(\n", "# train_val_df,\n", "# test_size=0.1111,\n", "# stratify=train_val_df[\"disease\"],\n", "# random_state=42\n", "# )\n", "\n", "# print(\"Train:\", len(train_df))\n", "# print(\"Val:\", len(val_df))\n", "# print(\"Test:\", len(test_df))\n", "\n", "# def convert_boxes_to_qwen_format(boxes_str):\n", "# try:\n", "# boxes_list = ast.literal_eval(boxes_str)\n", "# if not boxes_list:\n", "# return \"\"\n", "\n", "# best_box = max(\n", "# boxes_list,\n", "# key=lambda b: b.get(\"confidence\", 0) if isinstance(b, dict) else 0\n", "# )\n", "\n", "# if isinstance(best_box, dict):\n", "# x1, y1, x2, y2 = best_box[\"x1\"], best_box[\"y1\"], best_box[\"x2\"], best_box[\"y2\"]\n", "# else:\n", "# x1, y1, x2, y2 = best_box[:4]\n", "\n", "# return f\"{x1},{y1},{x2},{y2}\"\n", "\n", "# except Exception as e:\n", "# print(f\"Box parse error: {e}\")\n", "# return \"\"\n", "\n", "# def create_sample(row):\n", "# if not os.path.exists(row[\"image_path\"]):\n", "# raise FileNotFoundError(row[\"image_path\"])\n", "\n", "# image = Image.open(row[\"image_path\"]).convert(\"RGB\")\n", "# boxes_text = convert_boxes_to_qwen_format(row[\"heatmap_rescaled_boxes\"])\n", "\n", "# return {\n", "# \"messages\": [\n", "# {\n", "# \"role\": \"user\",\n", "# \"content\": [\n", "# {\"type\": \"text\", \"text\": instruction},\n", "# {\"type\": \"image\", \"image\": image}\n", "# ]\n", "# },\n", "# {\n", "# \"role\": \"assistant\",\n", "# \"content\": [\n", "# {\n", "# \"type\": \"text\",\n", "# \"text\": (\n", "# f\"Disease: {row['disease']}\\n\"\n", "# f\"Report: {row['radiology_report']}\\n\"\n", "# f\"BoundingBoxes: {boxes_text}\"\n", "# )\n", "# }\n", "# ]\n", "# }\n", "# ]\n", "# }\n", "\n", "# def build_dataset(split_df, name=\"split\"):\n", "# dataset = []\n", "# for idx, row in split_df.iterrows():\n", "# try:\n", "# dataset.append(create_sample(row))\n", "# except Exception as e:\n", "# print(f\"[{name}] Skipping row {idx}: {e}\")\n", "# print(f\"{name} samples: {len(dataset)}\")\n", "# return dataset\n", "\n", "\n", "# train_set = build_dataset(train_df, \"Train\")\n", "# val_set = build_dataset(val_df, \"Val\")\n", "# test_set = build_dataset(test_df, \"Test\")\n", "\n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "test_df.to_csv(\"test.csv\", index=False)\n", "val_df.to_csv(\"val.csv\", index=False)\n", "train_df.to_csv(\"train.csv\", index=False)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "FBRl6UxDIJgu", "outputId": "6e983620-8029-4bf5-c9e4-0c9c3635f6e9" }, "outputs": [ { "data": { "text/plain": [ "{'messages': [{'role': 'user',\n", " 'content': [{'type': 'text',\n", " 'text': 'You are a medical vision-language model specialized in chest X-ray interpretation. Analyze the image STRICTLY based on visible radiographic evidence. Do NOT infer diagnoses from clinical history, labels, devices, or non-specific cues.\\n\\n================================================\\nMANDATORY REASONING ORDER (NO EXCEPTIONS)\\n================================================\\n\\nStep 1: Describe ONLY what is visually assessed in the image.\\nStep 2: Identify which anatomical regions were examined and why.\\nStep 3: Explicitly state whether pulmonary edema, congestion, or pleural effusion is PRESENT or ABSENT based on visible evidence.\\nStep 4: Assign the disease label using ONLY Step 3.\\n\\n================================================\\nCHF DIAGNOSTIC CRITERIA (STRICT)\\n================================================\\n\\nCongestive Heart Failure (CHF) may be diagnosed ONLY if at least ONE of the following is CLEARLY and DEFINITELY visible:\\n\\n✔ Interstitial pulmonary edema (e.g., definite Kerley B lines)\\n✔ Alveolar pulmonary edema\\n✔ Pulmonary vascular congestion WITH true cephalization\\n✔ Definite pleural effusion attributable to heart failure\\n✔ Perihilar haze WITH coexisting interstitial or alveolar edema\\n\\n------------------------------------------------\\nNOT SUFFICIENT FOR CHF (DO NOT USE):\\n------------------------------------------------\\n✘ Cardiomegaly alone\\n✘ Prominent vessels without cephalization\\n✘ Mild, diffuse, or vague haziness\\n✘ Patchy opacity without edema pattern\\n✘ Atelectasis or scarring alone\\n✘ Presence of medical devices\\n\\n================================================\\nHARD NORMAL OVERRIDE (ABSOLUTE)\\n================================================\\n\\nIf ALL of the following are true:\\n- Lung fields are clear or near-clear\\n- NO definite pulmonary edema\\n- NO interstitial markings (Kerley lines)\\n- NO pleural effusion\\n\\nTHEN:\\n✔ Disease label MUST be: NORMAL\\n✔ CHF diagnosis is FORBIDDEN\\n\\nThis rule OVERRIDES cardiomegaly, vascular prominence, projection issues, or limited inspiration.\\n\\n================================================\\nUNCERTAINTY HANDLING (STRICT)\\n================================================\\n\\nIf findings require speculative language such as:\\n\"possible\", \"suspected\", \"could represent\", \"cannot exclude\", \"questionable\", \"likely artifact\"\\n\\nTHEN:\\n✔ Default to NORMAL\\n✔ Do NOT diagnose CHF\\n\\n================================================\\nBOUNDING BOX RULES (CRITICAL)\\n================================================\\n\\nBounding boxes are REQUIRED for BOTH NORMAL and CHF cases.\\n\\nBounding boxes:\\n- Indicate regions that were visually assessed\\n- Show HOW reported findings were evaluated\\n- Do NOT imply presence or absence of disease\\n\\nRules:\\n✔ Boxes MUST align with anatomical structures described in the report\\n✔ Boxes MUST correspond to evaluated regions (lungs, hila, costophrenic angles, heart)\\n✔ Normal cases MUST still include boxes over assessed normal structures\\n✘ Boxes must NOT be used to justify disease by themselves\\n✘ Do NOT place boxes on regions not discussed in the report\\n\\n================================================\\nHALLUCINATION PREVENTION (ZERO TOLERANCE)\\n================================================\\n\\n- Do NOT invent edema, effusions, or interstitial markings\\n- Do NOT describe findings not clearly visible\\n- Do NOT upgrade equivocal findings to disease\\n\\n================================================\\nOUTPUT FORMAT (EXACT)\\n================================================\\n\\nDisease: \\nReport: \\nBoundingBoxes: x1,y1,x2,y2 format>'},\n", " {'type': 'image',\n", " 'image': }]},\n", " {'role': 'assistant',\n", " 'content': [{'type': 'text',\n", " 'text': 'Disease: CHF\\nReport: cardiomegaly. patchy bibasilar opacities, which could represent atelectasis or edema. sternotomy wires. left sided cardiac pacer defibrillator with leads in the right atrium ventricle and coronary sinus. right sided lead is also present.\\nBoundingBoxes: 257,89,301,134'}]}]}" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_set[0]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "XmeYvK91Ad0k", "outputId": "3145990a-5f19-4005-feb0-006adda9611c" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Applying LoRA configuration...\n", "Unsloth: Making `model.base_model.model.model` require gradients\n", "Unsloth: Model does not have a default image size - using 512\n" ] } ], "source": [ "# Apply LoRA\n", "print(\"Applying LoRA configuration...\")\n", "model = FastVisionModel.get_peft_model(\n", " model,\n", " finetune_vision_layers=True,\n", " finetune_language_layers=True,\n", " finetune_attention_modules=True,\n", " finetune_mlp_modules=True,\n", " r=16,\n", " lora_alpha=16,\n", " lora_dropout=0,\n", " bias=\"none\",\n", " random_state=3407,\n", " use_rslora=False,\n", " loftq_config=None,\n", ")\n", "\n", "# Enable for training\n", "FastVisionModel.for_training(model)\n", "\n", "trainer = SFTTrainer(\n", " model=model,\n", " tokenizer=tokenizer,\n", " data_collator=UnslothVisionDataCollator(model, tokenizer),\n", " train_dataset=train_set,\n", " eval_dataset=val_set,\n", " args=SFTConfig(\n", " per_device_train_batch_size=2,\n", " gradient_accumulation_steps=4,\n", " num_train_epochs=15, \n", " warmup_steps=50,\n", " learning_rate=2e-4,\n", " logging_steps=10,\n", " optim=\"adamw_8bit\",\n", " weight_decay=0.001,\n", " lr_scheduler_type=\"linear\",\n", " seed=3407,\n", " output_dir=\"outputs\",\n", " report_to=\"none\",\n", "\n", " # Required for vision fine-tuning\n", " remove_unused_columns=False,\n", " dataset_text_field=\"\",\n", " dataset_kwargs={\"skip_prepare_dataset\": True},\n", " # max_length=512,\n", " max_length=2048,\n", " ),\n", ")\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 272 }, "id": "5Qne_2g4DLl3", "outputId": "50d4bdcf-c6ac-41da-a8a2-4b5197a13ae9" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "The model is already on multiple devices. Skipping the move to device specified in `args`.\n", "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Unsloth: Will smartly offload gradients to save VRAM!\n" ] }, { "data": { "text/html": [ "\n", "
\n", " \n", " \n", " [3685/4335 21:37:54 < 3:49:03, 0.05 it/s, Epoch 12.75/15]\n", "
\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StepTraining Loss
108.710300
203.673100
301.992900
400.763900
500.128200
600.105600
700.088900
800.085600
900.087200
1000.076800
1100.070600
1200.079000
1300.065800
1400.071000
1500.073400
1600.066700
1700.080900
1800.068900
1900.069600
2000.070700
2100.067400
2200.071200
2300.063700
2400.058600
2500.060600
2600.062000
2700.064600
2800.060100
2900.058400
3000.056600
3100.056100
3200.052300
3300.059400
3400.064900
3500.059400
3600.054800
3700.057300
3800.055900
3900.056400
4000.056300
4100.053700
4200.055800
4300.052900
4400.055500
4500.050900
4600.053500
4700.057000
4800.047900
4900.048900
5000.054000
5100.051200
5200.048200
5300.051000
5400.048500
5500.050000
5600.046600
5700.049100
5800.045100
5900.040200
6000.038800
6100.043000
6200.040600
6300.040100
6400.040600
6500.039500
6600.040300
6700.038700
6800.040200
6900.040600
7000.040100
7100.038000
7200.034900
7300.039900
7400.038800
7500.036100
7600.035600
7700.038900
7800.037300
7900.036100
8000.035700
8100.036800
8200.037300
8300.034600
8400.035500
8500.034100
8600.035700
8700.033600
8800.030300
8900.028900
9000.028700
9100.029400
9200.028800
9300.027600
9400.030500
9500.029000
9600.029400
9700.026900
9800.026900
9900.026400
10000.027300
10100.028700
10200.029900
10300.025300
10400.026600
10500.028200
10600.026800
10700.027500
10800.025300
10900.026100
11000.026100
11100.025200
11200.026200
11300.025700
11400.024500
11500.024900
11600.022500
11700.020100
11800.021100
11900.020000
12000.019200
12100.018700
12200.019200
12300.018700
12400.018200
12500.017500
12600.018300
12700.017000
12800.019800
12900.018400
13000.018700
13100.018500
13200.018500
13300.017200
13400.016500
13500.017000
13600.017500
13700.016900
13800.016400
13900.017900
14000.015300
14100.015300
14200.016600
14300.014200
14400.015700
14500.012200
14600.010400
14700.010900
14800.010200
14900.011500
15000.011000
15100.010100
15200.010100
15300.009400
15400.010500
15500.010800
15600.009200
15700.009800
15800.010200
15900.009500
16000.011100
16100.009600
16200.009300
16300.009400
16400.008100
16500.009200
16600.010300
16700.008200
16800.008400
16900.008600
17000.009000
17100.009100
17200.007800
17300.007700
17400.006700
17500.005200
17600.004900
17700.005400
17800.005200
17900.004800
18000.005000
18100.005400
18200.005200
18300.004500
18400.004700
18500.004700
18600.003800
18700.004100
18800.004000
18900.004800
19000.004400
19100.004700
19200.004300
19300.004100
19400.003900
19500.004000
19600.004300
19700.003900
19800.004700
19900.004200
20000.003600
20100.003700
20200.003600
20300.002500
20400.002300
20500.002200
20600.002000
20700.002000
20800.002800
20900.002700
21000.002300
21100.002400
21200.002200
21300.002000
21400.001700
21500.001800
21600.001900
21700.002000
21800.002200
21900.001900
22000.002200
22100.002100
22200.002000
22300.001900
22400.001700
22500.001600
22600.002200
22700.001700
22800.001900
22900.001600
23000.001800
23100.002000
23200.001400
23300.000800
23400.000800
23500.001000
23600.000900
23700.000700
23800.001100
23900.001000
24000.001000
24100.001000
24200.000800
24300.001000
24400.000900
24500.001100
24600.000700
24700.000800
24800.000900
24900.001000
25000.000800
25100.001000
25200.001100
25300.000800
25400.001000
25500.000800
25600.000600
25700.000700
25800.000900
25900.001300
26000.001000
26100.000800
26200.000600
26300.000500
26400.000600
26500.000400
26600.000400
26700.000500
26800.000400
26900.000300
27000.000500
27100.000500
27200.000400
27300.000400
27400.000500
27500.000500
27600.000400
27700.000400
27800.000400
27900.000600
28000.000400
28100.000400
28200.000300
28300.000400
28400.000300
28500.000500
28600.000600
28700.000500
28800.000600
28900.000700
29000.000300
29100.000400
29200.000400
29300.000300
29400.000300
29500.000300
29600.000300
29700.000400
29800.000300
29900.000300
30000.000300
30100.000200
30200.000500
30300.000300
30400.000100
30500.000300
30600.000200
30700.000200
30800.000200
30900.000200
31000.000100
31100.000200
31200.000200
31300.000300
31400.000200
31500.000100
31600.000200
31700.000100
31800.000200
31900.000100
32000.000100
32100.000100
32200.000100
32300.000100
32400.000100
32500.000100
32600.000100
32700.000100
32800.000100
32900.000100
33000.000100
33100.000100
33200.000100
33300.000100
33400.000100
33500.000100
33600.000100
33700.000100
33800.000100
33900.000100
34000.000100
34100.000100
34200.000100
34300.000100
34400.000100
34500.000100
34600.000100
34700.000100
34800.000000
34900.000100
35000.000100
35100.000000
35200.000000
35300.000100
35400.000000
35500.000000
35600.000000
35700.000000
35800.000000
35900.000100
36000.000000
36100.000000
36200.000000
36300.000000
36400.000000
36500.000000
36600.000100
36700.000000
36800.000000

" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "ename": "KeyboardInterrupt", "evalue": "", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mKeyboardInterrupt\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[8]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[43mtrainer\u001b[49m\u001b[43m.\u001b[49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/SHANIN/EyeGaze/CHEST/unsloth_compiled_cache/UnslothSFTTrainer.py:55\u001b[39m, in \u001b[36mprepare_for_training_mode..wrapper\u001b[39m\u001b[34m(self, *args, **kwargs)\u001b[39m\n\u001b[32m 53\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mmodel\u001b[39m\u001b[33m'\u001b[39m) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m.model, \u001b[33m\"\u001b[39m\u001b[33mfor_training\u001b[39m\u001b[33m\"\u001b[39m):\n\u001b[32m 54\u001b[39m \u001b[38;5;28mself\u001b[39m.model.for_training()\n\u001b[32m---> \u001b[39m\u001b[32m55\u001b[39m output = \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 56\u001b[39m \u001b[38;5;66;03m# Return inference mode\u001b[39;00m\n\u001b[32m 57\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[33m'\u001b[39m\u001b[33mmodel\u001b[39m\u001b[33m'\u001b[39m) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m.model, \u001b[33m\"\u001b[39m\u001b[33mfor_inference\u001b[39m\u001b[33m\"\u001b[39m):\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/llm/lib/python3.12/site-packages/transformers/trainer.py:2325\u001b[39m, in \u001b[36mTrainer.train\u001b[39m\u001b[34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[39m\n\u001b[32m 2323\u001b[39m hf_hub_utils.enable_progress_bars()\n\u001b[32m 2324\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m-> \u001b[39m\u001b[32m2325\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43minner_training_loop\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 2326\u001b[39m \u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[43m=\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 2327\u001b[39m \u001b[43m \u001b[49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[43m=\u001b[49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 2328\u001b[39m \u001b[43m \u001b[49m\u001b[43mtrial\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtrial\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 2329\u001b[39m \u001b[43m \u001b[49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[43m=\u001b[49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 2330\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/llm/lib/python3.12/site-packages/transformers/trainer.py:2674\u001b[39m, in \u001b[36mTrainer._inner_training_loop\u001b[39m\u001b[34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[39m\n\u001b[32m 2667\u001b[39m context = (\n\u001b[32m 2668\u001b[39m functools.partial(\u001b[38;5;28mself\u001b[39m.accelerator.no_sync, model=model)\n\u001b[32m 2669\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m i != \u001b[38;5;28mlen\u001b[39m(batch_samples) - \u001b[32m1\u001b[39m\n\u001b[32m 2670\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m.accelerator.distributed_type != DistributedType.DEEPSPEED\n\u001b[32m 2671\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m contextlib.nullcontext\n\u001b[32m 2672\u001b[39m )\n\u001b[32m 2673\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m context():\n\u001b[32m-> \u001b[39m\u001b[32m2674\u001b[39m tr_loss_step = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mtraining_step\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_items_in_batch\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 2676\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[32m 2677\u001b[39m args.logging_nan_inf_filter\n\u001b[32m 2678\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_torch_xla_available()\n\u001b[32m 2679\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m (torch.isnan(tr_loss_step) \u001b[38;5;129;01mor\u001b[39;00m torch.isinf(tr_loss_step))\n\u001b[32m 2680\u001b[39m ):\n\u001b[32m 2681\u001b[39m \u001b[38;5;66;03m# if loss is nan or inf simply add the average of previous logged losses\u001b[39;00m\n\u001b[32m 2682\u001b[39m tr_loss = tr_loss + tr_loss / (\u001b[32m1\u001b[39m + \u001b[38;5;28mself\u001b[39m.state.global_step - \u001b[38;5;28mself\u001b[39m._globalstep_last_logged)\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/SHANIN/EyeGaze/CHEST/unsloth_compiled_cache/UnslothSFTTrainer.py:1068\u001b[39m, in \u001b[36m_UnslothSFTTrainer.training_step\u001b[39m\u001b[34m(self, *args, **kwargs)\u001b[39m\n\u001b[32m 1066\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mtraining_step\u001b[39m(\u001b[38;5;28mself\u001b[39m, *args, **kwargs):\n\u001b[32m 1067\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m.maybe_activation_offload_context:\n\u001b[32m-> \u001b[39m\u001b[32m1068\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m.\u001b[49m\u001b[43mtraining_step\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m:91\u001b[39m, in \u001b[36m_unsloth_training_step\u001b[39m\u001b[34m(***failed resolving arguments***)\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/llm/lib/python3.12/site-packages/accelerate/accelerator.py:2852\u001b[39m, in \u001b[36mAccelerator.backward\u001b[39m\u001b[34m(self, loss, **kwargs)\u001b[39m\n\u001b[32m 2850\u001b[39m \u001b[38;5;28mself\u001b[39m.lomo_backward(loss, learning_rate)\n\u001b[32m 2851\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m-> \u001b[39m\u001b[32m2852\u001b[39m \u001b[43mloss\u001b[49m\u001b[43m.\u001b[49m\u001b[43mbackward\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/llm/lib/python3.12/site-packages/torch/_tensor.py:647\u001b[39m, in \u001b[36mTensor.backward\u001b[39m\u001b[34m(self, gradient, retain_graph, create_graph, inputs)\u001b[39m\n\u001b[32m 637\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m has_torch_function_unary(\u001b[38;5;28mself\u001b[39m):\n\u001b[32m 638\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m handle_torch_function(\n\u001b[32m 639\u001b[39m Tensor.backward,\n\u001b[32m 640\u001b[39m (\u001b[38;5;28mself\u001b[39m,),\n\u001b[32m (...)\u001b[39m\u001b[32m 645\u001b[39m inputs=inputs,\n\u001b[32m 646\u001b[39m )\n\u001b[32m--> \u001b[39m\u001b[32m647\u001b[39m \u001b[43mtorch\u001b[49m\u001b[43m.\u001b[49m\u001b[43mautograd\u001b[49m\u001b[43m.\u001b[49m\u001b[43mbackward\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 648\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgradient\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mretain_graph\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcreate_graph\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m=\u001b[49m\u001b[43minputs\u001b[49m\n\u001b[32m 649\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/llm/lib/python3.12/site-packages/torch/autograd/__init__.py:354\u001b[39m, in \u001b[36mbackward\u001b[39m\u001b[34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[39m\n\u001b[32m 349\u001b[39m retain_graph = create_graph\n\u001b[32m 351\u001b[39m \u001b[38;5;66;03m# The reason we repeat the same comment below is that\u001b[39;00m\n\u001b[32m 352\u001b[39m \u001b[38;5;66;03m# some Python versions print out the first line of a multi-line function\u001b[39;00m\n\u001b[32m 353\u001b[39m \u001b[38;5;66;03m# calls in the traceback and some print out the last line\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m354\u001b[39m \u001b[43m_engine_run_backward\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 355\u001b[39m \u001b[43m \u001b[49m\u001b[43mtensors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 356\u001b[39m \u001b[43m \u001b[49m\u001b[43mgrad_tensors_\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 357\u001b[39m \u001b[43m \u001b[49m\u001b[43mretain_graph\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 358\u001b[39m \u001b[43m \u001b[49m\u001b[43mcreate_graph\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 359\u001b[39m \u001b[43m \u001b[49m\u001b[43minputs_tuple\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 360\u001b[39m \u001b[43m \u001b[49m\u001b[43mallow_unreachable\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m 361\u001b[39m \u001b[43m \u001b[49m\u001b[43maccumulate_grad\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m 362\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/llm/lib/python3.12/site-packages/torch/autograd/graph.py:829\u001b[39m, in \u001b[36m_engine_run_backward\u001b[39m\u001b[34m(t_outputs, *args, **kwargs)\u001b[39m\n\u001b[32m 827\u001b[39m unregister_hooks = _register_logging_hooks_on_whole_graph(t_outputs)\n\u001b[32m 828\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m829\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mVariable\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_execution_engine\u001b[49m\u001b[43m.\u001b[49m\u001b[43mrun_backward\u001b[49m\u001b[43m(\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Calls into the C++ engine to run the backward pass\u001b[39;49;00m\n\u001b[32m 830\u001b[39m \u001b[43m \u001b[49m\u001b[43mt_outputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\n\u001b[32m 831\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# Calls into the C++ engine to run the backward pass\u001b[39;00m\n\u001b[32m 832\u001b[39m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[32m 833\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m attach_logging_hooks:\n", "\u001b[31mKeyboardInterrupt\u001b[39m: " ] } ], "source": [ "trainer.train()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-CryVNfYOQ27", "outputId": "2cc0325c-1aa4-4fd6-b5eb-fcd7ffdb8a6b" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Saving model...\n" ] }, { "data": { "text/plain": [ "[]" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Save the model\n", "print(\"Saving model...\")\n", "model.save_pretrained(\"EGD_lora\")\n", "tokenizer.save_pretrained(\"EGD_lora\")" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Original rows: 288\n", "Remaining rows: 76\n" ] } ], "source": [ "import pandas as pd\n", "import os\n", "\n", "# Load CSV\n", "df = pd.read_csv(\"/home/shanin/Desktop/SHANIN/EyeGaze/CHEST/test.csv\")\n", "\n", "# Remove rows where filename contains '_aug'\n", "df_clean = df[\n", " ~df[\"image_path\"].apply(\n", " lambda x: \"_aug\" in os.path.basename(x).lower()\n", " )\n", "]\n", "\n", "# Save\n", "df_clean.to_csv(\"/home/shanin/Desktop/SHANIN/EyeGaze/CHEST/test.csv\", index=False)\n", "\n", "print(\"Original rows:\", len(df))\n", "print(\"Remaining rows:\", len(df_clean))\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000, "referenced_widgets": [ "55d9488bfef24ec0bb696261664db48b", "88c32ffba0af4b61b7ccb315705d71fd", "0d9f25e7ccc34bf8a1a393ffecdd2423", "97c86a2d7d9d44b7a4d663c68b806054", "6dd95157f0874d59ba124934ea324e7d", "31118ef02e08414aa66cb5ff6e6c7514", "0cde70fedae0455fad85a009b0f05eae", "d76f682126cd47fea6e45a3e2879a20d", "544aa96debc740929b82bb98f5c048f0", "a3006a8cb1fc4c519e57c29d798b9768", "2d90c6ceff7d4e91a5313d4d8dcc2e31", "c950477fe178495ea399f5ad35b9c8aa", "6562de7b97b345908bf36ef141e3521b", "c360b40ba1ba44b498b63c21b43635e0", "f33d596931ca4662a90b2199bbca9ba4", "1d5fb1740e544f239878bc3abf3595bd", "92e8daf371734130b095b7facd5c34fa", "c141805d36ce4dd4bad0fff565c30e74", "697bf69e98aa49969c2074f7ab229a4f", "ed671b2d259c4acd96868ba7012c30bf", "3defc7194f144bdca601b0b959f606f1", "38d10bd1f94f4ecb985fcef0b9c521d3", "75c7c7a6c6b74632a67c29d7365a6a04", "ba4dd1ddfd874a9a8f99336e6ab61b3e", "f3f4a0470a4a4f95af5037b96575dbe7", "1d7359e227b34c4bab4cbdbc96e8f31c", "21ea92e08f104ddd8fccffe66d67eae1", "5a682e13d4c64e61a980b01c61d27239", "7109de9f466c4f32a925b76034584226", "f3dfbed832474773ae7b0daa520c7782", "3b24d1d17ad4449daec5abd4cffeabab", "d22190567cfb4fb09f06e30465ee4ecd", "18e00890879b4d85a77166fcb19518b8", "1237c5d0d49347ce8ff1ea88febfc00b", "513889de43264bf4a8d2743c9c678bf8", "6bcfe831f391453c9a0cb7a524ad64c0", "2064375e3eb640978ed0204e06c63daf", "4e990d4554ac495ba4831bf1e83c2eaf", "01a4aefee71f4f68875c2e3572db50ef", "bcdab2d95a204ee999cecc1f24afad1b", "02cf2676f874456f9a5b83012008d9ba", "70563f0b08e54f13a0d57b8541779018", "84fce999df6f4101904c5a46c0e4dfb4", "b364c8a6ebd6406bb183b0a764a1a523", "f2185a9d66e64032bce14f1fb1315925", "257a0377f2304eb58cc6c63a587acd8d", "9f707b2340454a81b381eea740ace9a3", "9f45ebf9037141148bed50d5e0647c64", "ee70e3f3d12d49ff8b3f8e210e27a00b", "b90a575197d84be191f960f1ab119b8d", "1756b6feb6624333a19808052f507e3e", "6c1d055b32b642198c97be66b927d446", "dc6dfa275de142db96a9c2b96c0b2f38", "c26640d94f3c46439750f9ee3bf8efde", "ea7ad5028b374f0ab5616881432292e3", "16b406993f82408ab1b1a4725af91fc5", "5744b578842944828708926de5d5c697", "38e15870dabc42bebcb1d0721463765f", "19f779edce12407d9abcd7f56874c267", "c69684207d6d4198933586a0b97b8d3c", "48233afee324459fa8d4dfcf332623c9", "471b153d9074476085266dc63a9e8453", "2a445e689b9345a38b672ac22b76a855", "96f078b15a5648fe8030ed4920aefbbc", "ac1faa8db0774e9f9bf25e422fca1fc5", "32850e5661db4e7a8db80f7c9e3797dd" ] }, "id": "k7rVmAZtQQUg", "outputId": "6722d8e3-2b8c-47c4-dec9-27eb270f3821" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "2026-01-15 10:48:18.140589: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", "[xformers|WARNING]WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:\n", " PyTorch 2.8.0+cu128 with CUDA None (you have 2.8.0+cu128)\n", " Python 3.12.11 (you have 3.12.11)\n", " Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)\n", " Memory-efficient attention, SwiGLU, sparse and more won't be available.\n", " Set XFORMERS_MORE_DETAILS=1 for more details\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "========\n", "Switching to PyTorch attention since your Xformers is broken.\n", "========\n", "\n", "Unsloth: Xformers was not installed correctly.\n", "Please install xformers separately first.\n", "Then confirm if it's correctly installed by running:\n", "python -m xformers.info\n", "\n", "Longer error message:\n", "xFormers can't load C++/CUDA extensions. xFormers was built for:\n", " PyTorch 2.8.0+cu128 with CUDA None (you have 2.8.0+cu128)\n", " Python 3.12.11 (you have 3.12.11)\n", " Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)\n", " Memory-efficient attention, SwiGLU, sparse and more won't be available.\n", "🦥 Unsloth Zoo will now patch everything to make training faster!\n", "Loading fine-tuned model...\n", "Unsloth: WARNING `trust_remote_code` is True.\n", "Are you certain you want to do remote code execution?\n", "==((====))== Unsloth 2025.11.4: Fast Qwen2_5_Vl patching. Transformers: 4.57.1.\n", " \\\\ /| NVIDIA GeForce RTX 3060. Num GPUs = 1. Max memory: 11.631 GB. Platform: Linux.\n", "O^O/ \\_/ \\ Torch: 2.8.0+cu128. CUDA: 8.6. CUDA Toolkit: 12.8. Triton: 3.4.0\n", "\\ / Bfloat16 = TRUE. FA [Xformers = None. FA2 = False]\n", " \"-____-\" Free license: http://github.com/unslothai/unsloth\n", "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n", "Unsloth: Qwen2_5_Vl does not support SDPA - switching to fast eager.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "The image processor of type `Qwen2VLImageProcessor` is now loaded as a fast processor by default, even if the model checkpoint was saved with a slow processor. This is a breaking change and may produce slightly different outputs. To continue using the slow processor, instantiate this class with `use_fast=False`. Note that this behavior will be extended to all models in a future release.\n" ] }, { "data": { "text/plain": [ "PeftModelForCausalLM(\n", " (base_model): LoraModel(\n", " (model): Qwen2_5_VLForConditionalGeneration(\n", " (model): Qwen2_5_VLModel(\n", " (visual): Qwen2_5_VisionTransformerPretrainedModel(\n", " (patch_embed): Qwen2_5_VisionPatchEmbed(\n", " (proj): Conv3d(3, 1280, kernel_size=(2, 14, 14), stride=(2, 14, 14), bias=False)\n", " )\n", " (rotary_pos_emb): Qwen2_5_VisionRotaryEmbedding()\n", " (blocks): ModuleList(\n", " (0-31): 32 x Qwen2_5_VLVisionBlock(\n", " (norm1): Qwen2RMSNorm((1280,), eps=1e-06)\n", " (norm2): Qwen2RMSNorm((1280,), eps=1e-06)\n", " (attn): Qwen2_5_VLVisionAttention(\n", " (qkv): lora.Linear(\n", " (base_layer): Linear(in_features=1280, out_features=3840, bias=True)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=1280, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=3840, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (proj): lora.Linear(\n", " (base_layer): Linear(in_features=1280, out_features=1280, bias=True)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=1280, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=1280, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " )\n", " (mlp): Qwen2_5_VLMLP(\n", " (gate_proj): lora.Linear(\n", " (base_layer): Linear(in_features=1280, out_features=3420, bias=True)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=1280, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=3420, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (up_proj): lora.Linear(\n", " (base_layer): Linear(in_features=1280, out_features=3420, bias=True)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=1280, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=3420, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (down_proj): lora.Linear(\n", " (base_layer): Linear(in_features=3420, out_features=1280, bias=True)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=3420, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=1280, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (act_fn): SiLUActivation()\n", " )\n", " )\n", " )\n", " (merger): Qwen2_5_VLPatchMerger(\n", " (ln_q): Qwen2RMSNorm((1280,), eps=1e-06)\n", " (mlp): Sequential(\n", " (0): Linear(in_features=5120, out_features=5120, bias=True)\n", " (1): GELU(approximate='none')\n", " (2): Linear(in_features=5120, out_features=3584, bias=True)\n", " )\n", " )\n", " )\n", " (language_model): Qwen2_5_VLTextModel(\n", " (embed_tokens): Embedding(152064, 3584)\n", " (layers): ModuleList(\n", " (0-27): 28 x Qwen2_5_VLDecoderLayer(\n", " (self_attn): Qwen2_5_VLAttention(\n", " (q_proj): lora.Linear4bit(\n", " (base_layer): Linear4bit(in_features=3584, out_features=3584, bias=True)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=3584, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=3584, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (k_proj): lora.Linear4bit(\n", " (base_layer): Linear4bit(in_features=3584, out_features=512, bias=True)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=3584, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=512, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (v_proj): lora.Linear4bit(\n", " (base_layer): Linear4bit(in_features=3584, out_features=512, bias=True)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=3584, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=512, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (o_proj): lora.Linear4bit(\n", " (base_layer): Linear4bit(in_features=3584, out_features=3584, bias=False)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=3584, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=3584, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (rotary_emb): Qwen2_5_VLRotaryEmbedding()\n", " )\n", " (mlp): Qwen2MLP(\n", " (gate_proj): lora.Linear4bit(\n", " (base_layer): Linear4bit(in_features=3584, out_features=18944, bias=False)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=3584, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=18944, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (up_proj): lora.Linear4bit(\n", " (base_layer): Linear4bit(in_features=3584, out_features=18944, bias=False)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=3584, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=18944, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (down_proj): lora.Linear4bit(\n", " (base_layer): Linear4bit(in_features=18944, out_features=3584, bias=False)\n", " (lora_dropout): ModuleDict(\n", " (default): Identity()\n", " )\n", " (lora_A): ModuleDict(\n", " (default): Linear(in_features=18944, out_features=16, bias=False)\n", " )\n", " (lora_B): ModuleDict(\n", " (default): Linear(in_features=16, out_features=3584, bias=False)\n", " )\n", " (lora_embedding_A): ParameterDict()\n", " (lora_embedding_B): ParameterDict()\n", " (lora_magnitude_vector): ModuleDict()\n", " )\n", " (act_fn): SiLUActivation()\n", " )\n", " (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)\n", " (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)\n", " )\n", " )\n", " (norm): Qwen2RMSNorm((3584,), eps=1e-06)\n", " (rotary_emb): Qwen2_5_VLRotaryEmbedding()\n", " )\n", " )\n", " (lm_head): Linear(in_features=3584, out_features=152064, bias=False)\n", " )\n", " )\n", ")" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\n", "import torch\n", "from PIL import Image\n", "from unsloth import FastVisionModel\n", "from transformers import AutoProcessor\n", "import json\n", "\n", "# Load the fine-tuned model\n", "print(\"Loading fine-tuned model...\")\n", "model, tokenizer = FastVisionModel.from_pretrained(\n", " \"EGD_lora\", # Your saved model\n", " load_in_4bit=True,\n", " trust_remote_code=True,\n", ")\n", "\n", "# Load the original processor (or create it from the tokenizer)\n", "from transformers import Qwen2_5_VLForConditionalGeneration, Qwen2VLImageProcessor\n", "\n", "# Load the original model's processor\n", "processor = AutoProcessor.from_pretrained(\"Qwen/Qwen2.5-VL-7B-Instruct\", trust_remote_code=True)\n", "FastVisionModel.for_inference(model)\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "WZWcxt1qxFN0" }, "outputs": [], "source": [ "import pandas as pd\n", "from PIL import Image\n", "import torch\n", "\n", "def run_inference(image_path, instruction=None):\n", " if instruction is None:\n", " instruction = (\n", " \"You are a medical vision-language model specialized in chest X-ray interpretation. \"\n", " \"Analyze the image STRICTLY based on visible radiographic evidence. \"\n", " \"Do NOT infer diagnoses from clinical history, labels, devices, or non-specific cues.\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"MANDATORY REASONING ORDER (NO EXCEPTIONS)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"Step 1: Describe ONLY what is visually assessed in the image.\\n\"\n", " \"Step 2: Identify which anatomical regions were examined and why.\\n\"\n", " \"Step 3: Explicitly state whether pulmonary edema, congestion, or pleural effusion \"\n", " \"is PRESENT or ABSENT based on visible evidence.\\n\"\n", " \"Step 4: Assign the disease label using ONLY Step 3.\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"CHF DIAGNOSTIC CRITERIA (STRICT)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"Congestive Heart Failure (CHF) may be diagnosed ONLY if at least ONE of the following \"\n", " \"is CLEARLY and DEFINITELY visible:\\n\\n\"\n", "\n", " \"✔ Interstitial pulmonary edema (e.g., definite Kerley B lines)\\n\"\n", " \"✔ Alveolar pulmonary edema\\n\"\n", " \"✔ Pulmonary vascular congestion WITH true cephalization\\n\"\n", " \"✔ Definite pleural effusion attributable to heart failure\\n\"\n", " \"✔ Perihilar haze WITH coexisting interstitial or alveolar edema\\n\\n\"\n", "\n", " \"------------------------------------------------\\n\"\n", " \"NOT SUFFICIENT FOR CHF (DO NOT USE):\\n\"\n", " \"------------------------------------------------\\n\"\n", "\n", " \"✘ Cardiomegaly alone\\n\"\n", " \"✘ Prominent vessels without cephalization\\n\"\n", " \"✘ Mild, diffuse, or vague haziness\\n\"\n", " \"✘ Patchy opacity without edema pattern\\n\"\n", " \"✘ Atelectasis or scarring alone\\n\"\n", " \"✘ Presence of medical devices\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"HARD NORMAL OVERRIDE (ABSOLUTE)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"If ALL of the following are true:\\n\"\n", " \"- Lung fields are clear or near-clear\\n\"\n", " \"- NO definite pulmonary edema\\n\"\n", " \"- NO interstitial markings (Kerley lines)\\n\"\n", " \"- NO pleural effusion\\n\\n\"\n", "\n", " \"THEN:\\n\"\n", " \"✔ Disease label MUST be: NORMAL\\n\"\n", " \"✔ CHF diagnosis is FORBIDDEN\\n\\n\"\n", "\n", " \"This rule OVERRIDES cardiomegaly, vascular prominence, \"\n", " \"projection issues, or limited inspiration.\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"UNCERTAINTY HANDLING (STRICT)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"If findings require speculative language such as:\\n\"\n", " \"\\\"possible\\\", \\\"suspected\\\", \\\"could represent\\\", \"\n", " \"\\\"cannot exclude\\\", \\\"questionable\\\", \\\"likely artifact\\\"\\n\\n\"\n", "\n", " \"THEN:\\n\"\n", " \"✔ Default to NORMAL\\n\"\n", " \"✔ Do NOT diagnose CHF\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"BOUNDING BOX RULES (CRITICAL)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"Bounding boxes are REQUIRED for BOTH NORMAL and CHF cases.\\n\\n\"\n", "\n", " \"Bounding boxes:\\n\"\n", " \"- Indicate regions that were visually assessed\\n\"\n", " \"- Show HOW reported findings were evaluated\\n\"\n", " \"- Do NOT imply presence or absence of disease\\n\\n\"\n", "\n", " \"Rules:\\n\"\n", " \"✔ Boxes MUST align with anatomical structures described in the report\\n\"\n", " \"✔ Boxes MUST correspond to evaluated regions \"\n", " \"(lungs, hila, costophrenic angles, heart)\\n\"\n", " \"✔ Normal cases MUST still include boxes over assessed normal structures\\n\"\n", " \"✘ Boxes must NOT be used to justify disease by themselves\\n\"\n", " \"✘ Do NOT place boxes on regions not discussed in the report\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"HALLUCINATION PREVENTION (ZERO TOLERANCE)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"- Do NOT invent edema, effusions, or interstitial markings\\n\"\n", " \"- Do NOT describe findings not clearly visible\\n\"\n", " \"- Do NOT upgrade equivocal findings to disease\\n\\n\"\n", "\n", " \"================================================\\n\"\n", " \"OUTPUT FORMAT (EXACT)\\n\"\n", " \"================================================\\n\\n\"\n", "\n", " \"Disease: \\n\"\n", " \"Report: \\n\"\n", " \"BoundingBoxes: x1,y1,x2,y2 format>\"\n", " )\n", "\n", "\n", " image = Image.open(image_path).convert('RGB')\n", "\n", " messages = [\n", " {\n", " \"role\": \"user\",\n", " \"content\": [\n", " {\"type\": \"image\", \"image\": image},\n", " {\"type\": \"text\", \"text\": instruction}\n", " ]\n", " }\n", " ]\n", "\n", " text = tokenizer.apply_chat_template(\n", " messages,\n", " tokenize=False,\n", " add_generation_prompt=True\n", " )\n", "\n", " inputs = processor(\n", " text=[text],\n", " images=[image],\n", " return_tensors=\"pt\",\n", " padding=True,\n", " )\n", "\n", " inputs = {k: v.to(\"cuda\") for k, v in inputs.items()}\n", "\n", " with torch.no_grad():\n", " generated_ids = model.generate(\n", " **inputs,\n", " max_new_tokens=256,\n", " temperature=0.1,\n", " top_p=0.9,\n", " # do_sample=True,\n", " do_sample=False,\n", " pad_token_id=tokenizer.pad_token_id,\n", " eos_token_id=tokenizer.eos_token_id,\n", " )\n", "\n", " generated_ids = generated_ids[:, inputs['input_ids'].shape[1]:]\n", " response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]\n", "\n", " return response\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "id": "mA3FFjDzcWVO" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Row: 1\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/116c787f-3423c257-151f5943-ae7bd2ff-b7f0c496.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. patchy bibasilar opacities, which could represent atelectasis or edema. sternotomy wires. left sided cardiac pacer defibrillator with leads in the right atrium ventricle and coronary sinus. right sided lead is also present.\n", "Ground Truth BBox: 257,89,301,134\n", "Predicted Disease: chf\n", "Predicted Report: Report: left sided cardiac pacer with leads projecting over the right atrium and ventricle. prominent heart. aortic calcifications. lungs are clear.\n", "Predicted BoundingBoxes: ['150,186,199,223']\n", "------------------------------------------------------------\n", "Row: 2\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/2c466a34-8db99db4-27bcd765-38a47cbd-3a16cc3e.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: left-sided cardiac defibrillator with lead in the right ventricle. enlarged heart. left costophrenic angle is not included. left lung base is not included. small right effusion is suspected. vague haziness in the right mid lung. probably artifactual but could represent pneumonia.\n", "Ground Truth BBox: 100,160,168,234\n", "Predicted Disease: chf\n", "Predicted Report: Report: left sided cardiac pacer with leads projecting over the right atrium and ventricle. prominent heart. aortic calcifications. lungs are clear.\n", "Predicted BoundingBoxes: ['190,106,245,153']\n", "------------------------------------------------------------\n", "Row: 3\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/958653fa-56af9e10-318e69a7-abaf2cc0-62e382de.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. slightly prominent heart. no pleural effusion. lungs appear normal. no pneumothorax. necklace noted at the neck.\n", "Ground Truth BBox: 221,127,266,178\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. slight haziness at the bases, could be normal or could represent mild congestion. no effusion or pneumothorax.\n", "Predicted BoundingBoxes: ['85,189,141,259']\n", "------------------------------------------------------------\n", "Row: 4\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/291a3ece-3412be54-831054c7-47c35f08-b179cc2f.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. mild thoracic spinal degeneration. lungs are clear. mild cervical spinal degeneration.\n", "Ground Truth BBox: 152,113,224,311\n", "Predicted Disease: normal\n", "Predicted Report: Report: the lungs are clear. normal heart. soft tissues and bones normal.\n", "Predicted BoundingBoxes: ['181,113,246,215']\n", "------------------------------------------------------------\n", "Row: 5\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/b772f053-63468411-84270890-1c3c09b7-ea75dee6.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs. normal bones and soft tissues.\n", "Ground Truth BBox: 342,40,388,81\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['193,156,238,196']\n", "------------------------------------------------------------\n", "Row: 6\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/402ec1ad-8a7ec057-bd0d04ec-2db0bbb5-44ebc4ed.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 189,113,240,156\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['52,145,115,186']\n", "------------------------------------------------------------\n", "Row: 7\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/cb1f25ef-87f09c2a-0f656ffe-f63022ab-8b305520.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: prominent heart. low lung volumes. left basilar opacity difficult to determine due to heart position. there may be small bilateral effusions with suspected patchy opacity of both bases.\n", "Ground Truth BBox: 99,240,144,280\n", "Predicted Disease: chf\n", "Predicted Report: Report: mild cardiomegaly. lungs are clear.\n", "Predicted BoundingBoxes: ['90,148,150,202']\n", "------------------------------------------------------------\n", "Row: 8\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/41f4628d-3a6c7bdf-83f3187d-179970df-a99f7a86.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal lungs. no pleural effusion. no pneumothorax. aortic calcifications. normal heart.\n", "Ground Truth BBox: 65,335,120,388\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['205,77,252,142']\n", "------------------------------------------------------------\n", "Row: 9\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/a1030f13-afc2d3d2-f194ebd1-e5a24299-0e09321f.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear.\n", "Ground Truth BBox: 131,254,167,298\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['168,45,228,144']\n", "------------------------------------------------------------\n", "Row: 10\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/f3a785c1-784233ee-57d4524a-7f26f6b4-f1f8d497.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: lung bases not entirely included. cardiomegaly. hyper-inflated lungs with areas of scarring. patchy opacity in the perihilar and lower lobes bilateral. bilaterally probably edema or infection.\n", "Ground Truth BBox: 204,204,244,251\n", "Predicted Disease: chf\n", "Predicted Report: Report: lung bases are not completely included. cardiomegaly. hyper-inflated lungs with areas of scarring. patchy opacity in the perihilar and lower lobes bilateral. bilaterally probably edema or infection.\n", "Predicted BoundingBoxes: ['265,194,304,234']\n", "------------------------------------------------------------\n", "Row: 11\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/29bdb8bb-bacbe53c-f4a892e6-3cfc384e-bc7b3897.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: sternotomy wires. cardiomegaly. moderate pleural right minor fissure. bilateral effusions right greater than the left with atelectasis or consolidation.\n", "Ground Truth BBox: 52,135,133,200\n", "Predicted Disease: chf\n", "Predicted Report: Report: sternotomy wires. cardiomegaly. generalized opacity at the bases. probably edema. small effusions suspected. there is some fluid in the right minor fissure. aortic valve. prosthesis.\n", "Predicted BoundingBoxes: ['350,268,416,329']\n", "------------------------------------------------------------\n", "Row: 12\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/d570b545-7871b706-67c58c73-3f24d518-5fb7a23d.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: prominent heart. the patient is lordodically positioned. patchy opacity in the right mid lung and at the right base. probably atelectasis or scarring. suspect a pleural plaque at the left base as well as peripherally at the left lateral pleura. thoracic spinal degeneration.\n", "Ground Truth BBox: 164,172,215,238\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. small bilateral effusions with generalized haziness in the lungs. it's compatible with edema. thoracic spinal degeneration. right ac joint arthritis.\n", "Predicted BoundingBoxes: ['0,23,54,78']\n", "------------------------------------------------------------\n", "Row: 13\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/9c091aff-03c78569-de7a251d-f2a35adb-ff89fa02.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. limited evaluation of the lungs due to high contrast technique. no large effusion or pneumothorax.\n", "Ground Truth BBox: 125,0,161,25\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Predicted BoundingBoxes: ['18,250,61,289']\n", "------------------------------------------------------------\n", "Row: 14\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/02d7845f-0120d2f5-7dd7585d-ba0d6767-e6038823.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear. right lung base is not completely included.\n", "Ground Truth BBox: 200,91,244,134\n", "Predicted Disease: normal\n", "Predicted Report: Report: lungs are clear. no pleural effusion or pneumothorax. normal heart size and mediastinum. no pneumothorax or pleural effusion.\n", "Predicted BoundingBoxes: ['366,210,416,259']\n", "------------------------------------------------------------\n", "Row: 15\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/e8bc2bd1-549efb3d-001ba3a3-ece3b4f9-897ba73b.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs, right greater than left. prominent pulmonary vessels. suspect mild congestion or pulmonary edema.\n", "Ground Truth BBox: 54,243,100,288\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs. prominent pulmonary vessels. kerley b lines on the right. this could represent mild pulmonary edema.\n", "Predicted BoundingBoxes: ['53,174,98,224']\n", "------------------------------------------------------------\n", "Row: 16\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/feefc68a-0a26d0a0-65e4a2a0-b1efc19d-0abcd7d1.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs.\n", "Ground Truth BBox: 243,262,279,306\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['193,156,238,206']\n", "------------------------------------------------------------\n", "Row: 17\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/4ff79c8d-fd7de62b-52ffeb40-2fe8ccfc-f12beb41.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: the chin obscures the lung apices. low lung volumes. dense opacity at the bases bilaterally. probably pleural effusion with edema or infection or atelectasis. prominent heart.\n", "Ground Truth BBox: 265,187,400,298\n", "Predicted Disease: chf\n", "Predicted Report: Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Predicted BoundingBoxes: ['50,189,128,251']\n", "------------------------------------------------------------\n", "Row: 18\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/7b2baa0e-0ccd9471-aeb95bf7-c991b526-85690b9d.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear.\n", "Ground Truth BBox: 177,154,219,199\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['197,157,251,206']\n", "------------------------------------------------------------\n", "Row: 19\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/16948ae4-b8be1fa1-6b1fa93f-30dcaa87-cb904cd1.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: right lung is not completely included. lungs appear clear. no large effusion or pneumothorax. normal heart and mediastinum.\n", "Ground Truth BBox: 202,140,277,191\n", "Predicted Disease: normal\n", "Predicted Report: Report: lungs are clear. no pleural effusion or pneumothorax. normal heart size and mediastinum. lungs and soft tissues normal.\n", "Predicted BoundingBoxes: ['369,214,416,261']\n", "------------------------------------------------------------\n", "Row: 20\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/efb03b13-c411b791-e39310a3-982c0a38-1100ccc8.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. elevated right lung base may be due to a large effusion. there is some haziness of the lungs suggesting atelectasis. prominent breast shadow at the left, lung base.\n", "Ground Truth BBox: 65,98,134,190\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. slight haziness at the bases, could be normal or could represent mild congestion. no effusion or pneumothorax.\n", "Predicted BoundingBoxes: ['90,136,151,258']\n", "------------------------------------------------------------\n", "Row: 21\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/3158f4e8-6a034072-b052d188-f4f3b37d-561fff8b.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: patchy bibasilar opacity with cardiomegaly. this could represent edema but infection is also a strong consideration. no pleural effusion or pneumothorax.\n", "Ground Truth BBox: 81,189,163,264\n", "Predicted Disease: chf\n", "Predicted Report: Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Predicted BoundingBoxes: ['45,91,124,218']\n", "------------------------------------------------------------\n", "Row: 22\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/cac3fd9e-f85b2b92-f2109fbb-fe266c7e-41fc8c41.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart. normal mediastinum. normal lungs. normal bones and soft tissues.\n", "Ground Truth BBox: 198,73,276,169\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['316,220,359,257']\n", "------------------------------------------------------------\n", "Row: 23\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/1e4d4d01-657d797c-f09f7a14-cc14e092-909e66b8.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: normal heart and mediastinum. prominent pulmonary vasculature. no focal consolidation, pleural effusion or pneumothorax.\n", "Ground Truth BBox: 208,0,244,39\n", "Predicted Disease: chf\n", "Predicted Report: Report: prominent heart. small left effusion with atelectasis. probable trace right effusion as well. the lungs show patchy opacity, most pronounced at the right base, which is not specific. probably edema, but infection is possible as well.\n", "Predicted BoundingBoxes: ['305,214,387,291']\n", "------------------------------------------------------------\n", "Row: 24\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/865de6c6-25704eab-a1f495cf-d8d2bdc3-f3e35f36.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs. thoracic spinal degeneration.\n", "Ground Truth BBox: 148,75,244,236\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['90,68,151,128']\n", "------------------------------------------------------------\n", "Row: 25\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/46b6d27f-05fc0509-a106934d-8b60e412-be2d97bb.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: elevated right lung base. cardiomegaly. prominent pulmonary vessels. lungs may be congested. no focal consolidation pleural effusion or pneumothorax.\n", "Ground Truth BBox: 219,93,266,218\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. small bilateral effusions with generalized haziness in the lungs. it's compatible with edema. thoracic spinal degeneration. right ac joint arthritis.\n", "Predicted BoundingBoxes: ['39,130,111,230']\n", "------------------------------------------------------------\n", "Row: 26\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/1a3fc5d7-b29579b6-beaf54aa-a7fde4bc-84ed8700.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal lungs. normal heart and mediastinum soft tissues and bones appear normal.\n", "Ground Truth BBox: 159,64,243,156\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['197,107,275,186']\n", "------------------------------------------------------------\n", "Row: 27\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/9a177679-9e809e56-552b0650-230b9dc0-ee2f5a9c.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart questionable midlung opacity of the lower hemithorax could represent a hiatal hernia. the lungs are clear.\n", "Ground Truth BBox: 112,70,156,107\n", "Predicted Disease: normal\n", "Predicted Report: Report: lung apices not completely included. normal heart and mediastinum. lungs are clear as visualized.\n", "Predicted BoundingBoxes: ['142,0,179,31']\n", "------------------------------------------------------------\n", "Row: 28\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/7fd82f55-aaba4935-f5b31bae-0288291b-82128657.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear. normal bones and soft tissues.\n", "Ground Truth BBox: 166,127,229,217\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['163,106,225,160']\n", "------------------------------------------------------------\n", "Row: 29\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/955211b8-735186c6-69e732c9-36206c53-a584f3eb.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. patchy opacity bilaterally at the bases. kerley b lines at the left lung base. small effusion suspected. this is the appearance of pulmonary edema.\n", "Ground Truth BBox: 304,222,373,312\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. small left effusion with atelectasis. probable trace right effusion as well. the lungs may be hyper-inflated as well. aortic calcifications.\n", "Predicted BoundingBoxes: ['37,230,116,269']\n", "------------------------------------------------------------\n", "Row: 30\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/c3a8a376-a4621465-bb65ba5d-d8dd3daa-e3e005eb.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. patchy atelectasis at the bases.\n", "Ground Truth BBox: 181,128,218,178\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. slight haziness at the bases, could be normal or could represent mild congestion. no effusion or pneumothorax.\n", "Predicted BoundingBoxes: ['358,260,416,339']\n", "------------------------------------------------------------\n", "Row: 31\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/9d9cf045-134d30f9-ffba3d5f-3a145094-80569824.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: prominent heart. prominent perihilar opacity. mediastinum is normal.\n", "Ground Truth BBox: 281,168,327,204\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Predicted BoundingBoxes: ['197,99,244,146']\n", "------------------------------------------------------------\n", "Row: 32\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/6bcb54fc-797bee0c-5d0b72b7-4b4c2763-e3deef1e.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiac clips. sternotomy wires. prominent heart. aortic calcifications. questionable right infrahilar opacity could be artifactual or could represent atelectasis or early infiltrate.\n", "Ground Truth BBox: 70,188,130,291\n", "Predicted Disease: chf\n", "Predicted Report: Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Predicted BoundingBoxes: ['357,293,416,338']\n", "------------------------------------------------------------\n", "Row: 33\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/689f0cd0-ee982281-95438dd2-a6b493b7-d50387b7.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: normal heart and mediastinum. aortic calcifications. normal lungs.\n", "Ground Truth BBox: 196,99,262,146\n", "Predicted Disease: chf\n", "Predicted Report: Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Predicted BoundingBoxes: ['317,226,360,262']\n", "------------------------------------------------------------\n", "Row: 34\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/e04f3597-e6cdfe8d-68111116-ad5c5cfd-30ac5867.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: lungs are clear. sternotomy wires. normal heart size. aortic calcifications.\n", "Ground Truth BBox: 171,53,273,165\n", "Predicted Disease: chf\n", "Predicted Report: Report: lungs are clear. no pleural effusion or pneumothorax. normal heart.\n", "Predicted BoundingBoxes: ['328,225,370,261']\n", "------------------------------------------------------------\n", "Row: 35\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/2b98791e-59dca4a7-d62cd907-a81f3bf8-3fe8cd44.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: normal heart. hazy opacity over the lower lungs bilaterally. lungs may be hyper-inflated. suspect pulmonary congestion. no pleural effusion or pneumothorax.\n", "Ground Truth BBox: 251,160,339,226\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs. prominent pulmonary vessels. kerley b lines on the right. this could represent mild pulmonary edema.\n", "Predicted BoundingBoxes: ['53,151,95,189']\n", "------------------------------------------------------------\n", "Row: 36\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/5c405cb5-414df3fd-57a04c46-8d9c7771-612e2672.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: right sided chest port with its tip in the superior vena cava. normal heart. aortic calcifications. thoracic spinal degeneration. lungs are clear.\n", "Ground Truth BBox: 21,100,81,171\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['205,96,252,158']\n", "------------------------------------------------------------\n", "Row: 37\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/f716ed09-e6c2f65e-1212e3be-7e8cc983-f9633985.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 197,59,244,120\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['193,106,238,144']\n", "------------------------------------------------------------\n", "Row: 38\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/2ffee6f3-02abd58a-f1c78e0f-7689bf17-f69ea741.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. part of the right heart border is obscured by right sided pleural effusion with atelectasis or consolidation. small amount of fluid in the right minor fissure. reticulonodular opacities throughout the lung apices bilaterally could represent fibrosis or chronic infectious process. no pneumothorax.\n", "Ground Truth BBox: 84,176,207,248\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. patchy opacity in the right lung base, could represent atelectasis, infection or edema. there may be a small right effusion.\n", "Predicted BoundingBoxes: ['312,216,381,300']\n", "------------------------------------------------------------\n", "Row: 39\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/669e6e09-9072a04c-c8f9766f-6c877cb6-01239dfd.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs. normal bones and soft tissues.\n", "Ground Truth BBox: 69,28,117,87\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['193,106,240,142']\n", "------------------------------------------------------------\n", "Row: 40\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/24c7496c-d7635dfe-b8e0b87f-d818affc-78ff7cf4.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Ground Truth BBox: 45,338,86,386\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. mild haziness of the lungs could represent minimal congestion. no focal consolidation, pleural effusion or pneumothorax.\n", "Predicted BoundingBoxes: ['358,316,416,380']\n", "------------------------------------------------------------\n", "Row: 41\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/655ca63b-91739e04-2121ab41-bb8734f9-d8fcd64b.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear.\n", "Ground Truth BBox: 213,120,262,173\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart. aortic calcifications. lungs are clear.\n", "Predicted BoundingBoxes: ['223,106,276,158']\n", "------------------------------------------------------------\n", "Row: 42\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/21fc8b35-43aaab0e-db4630fd-8ecebbb4-6eba92e6.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: low lung volumes. prominent heart. band of atelectasis at the right base. no pleural effusion or pneumothorax.\n", "Ground Truth BBox: 87,146,163,191\n", "Predicted Disease: normal\n", "Predicted Report: Report: prominent heart. lungs are clear.\n", "Predicted BoundingBoxes: ['178,104,245,165']\n", "------------------------------------------------------------\n", "Row: 43\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/41183cc7-29fa548f-28a3348b-7ab3dfc8-162c2882.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: right lung base is not entirely included. normal lungs. no left pleural effusion. no pneumothorax. normal heart. bones and soft tissues appear normal.\n", "Ground Truth BBox: 0,265,42,318\n", "Predicted Disease: normal\n", "Predicted Report: Report: lung apices not completely included. normal heart and mediastinum. lungs are clear as visualized.\n", "Predicted BoundingBoxes: ['163,0,201,25']\n", "------------------------------------------------------------\n", "Row: 44\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/80b49786-88a74899-70e7ecab-98cc7ca9-261155eb.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: prominent heart. elevated right lung base. there may be a small left effusion. no, focal consolidation. no pneumothorax.\n", "Ground Truth BBox: 318,330,397,396\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. thoracic spinal degeneration. lungs are clear.\n", "Predicted BoundingBoxes: ['87,158,149,262']\n", "------------------------------------------------------------\n", "Row: 45\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/ea543c1f-a2c5721c-d49e3110-946dde27-06a1f23f.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. aortic calcifications. haziness at the bases bilaterally. suspect small left effusion. kerley b lines on the right. prominent pulmonary vasculature. suspect pulmonary edema.\n", "Ground Truth BBox: 318,289,362,326\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs. prominent pulmonary vessels. kerley b lines on the right. this could represent mild pulmonary edema.\n", "Predicted BoundingBoxes: ['44,206,94,271']\n", "------------------------------------------------------------\n", "Row: 46\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/07e1e6bf-1d6d9740-10f021c0-0a8229f8-2297c5ef.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. left lung is not completely included. no large effusion. lungs are clear as visualized. no pneumothorax. minimal thoracic spinal degeneration.\n", "Ground Truth BBox: 341,71,416,139\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['209,104,253,141']\n", "------------------------------------------------------------\n", "Row: 47\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/27d78392-c6742897-792df26a-12210f36-65052f2f.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: severe cardiomegaly. patchy opacity in the right infrahilar region. could represent edema or atelectasis or pneumonia. left lung base is obscured by the heart\n", "Ground Truth BBox: 81,145,269,233\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. patchy opacity in the right lung base, could represent atelectasis, infection or edema. there may be a small right effusion.\n", "Predicted BoundingBoxes: ['297,194,358,231']\n", "------------------------------------------------------------\n", "Row: 48\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/3585208b-6a11bfad-bea7b95e-71894d45-ce2303f5.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear. thoracic spinal degeneration.\n", "Ground Truth BBox: 161,223,205,261\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['193,154,238,193']\n", "------------------------------------------------------------\n", "Row: 49\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/257c9f52-0f0c9004-994dbd15-522a597e-912b68fa.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs.\n", "Ground Truth BBox: 199,68,275,215\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['193,68,238,181']\n", "------------------------------------------------------------\n", "Row: 50\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/33ca3ff6-93eeef9a-924a08de-e2b8309a-b757adfa.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: mild cardiomegaly. patchy perihilar opacity bilaterally could represent mild edema or infection. right costophrenic angle is not completely included. left costrophrenic angle is not completely included. there is a nonspecific metallic density projecting in the right cardiophrenic angle.\n", "Ground Truth BBox: 81,130,182,282\n", "Predicted Disease: chf\n", "Predicted Report: Report: mild cardiomegaly. patchy perihilar opacity bilaterally could represent mild edema or infection. right costophrenic angle is not completely included. left costrophrenic angle is not completely included. there is a nodule or a calcification in the left upper lung. no pneumothorax.\n", "Predicted BoundingBoxes: ['207,199,250,260']\n", "------------------------------------------------------------\n", "Row: 51\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/62f2a462-83750eca-c384d41e-51503453-7459f59d.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: enlarged heart. aortic calcifications. lungs are clear. no pleural effusion or pneumothorax.\n", "Ground Truth BBox: 72,258,119,313\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. small left effusion with atelectasis. probable trace right effusion as well. the lungs may be hyper-inflated as well. aortic calcifications.\n", "Predicted BoundingBoxes: ['297,251,378,309']\n", "------------------------------------------------------------\n", "Row: 52\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/82f43a3b-f8b67cde-6ea58061-6f145d11-266b9f40.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear. no pleural effusion or pneumothorax. bones and soft tissues normal.\n", "Ground Truth BBox: 126,189,184,234\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart. aortic calcifications. lungs are clear.\n", "Predicted BoundingBoxes: ['201,106,256,181']\n", "------------------------------------------------------------\n", "Row: 53\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/0f502a52-7d8fb5f0-91fd0fa6-39f88d77-b6f57c7f.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal lungs. aortic calcifications. normal heart.\n", "Ground Truth BBox: 50,92,93,128\n", "Predicted Disease: normal\n", "Predicted Report: Report: prominent heart. low lung volumes. no focal consolidation, pleural effusion or pneumothorax.\n", "Predicted BoundingBoxes: ['90,48,149,147']\n", "------------------------------------------------------------\n", "Row: 54\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/0b79395e-dccedfe8-af5b2694-f13872f0-516e4c8b.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: sternotomy wires. left-sided cardiac pacer with leads projecting over the right atrium and ventricle. cardiomegaly. prominent pulmonary vessels. mild haziness of the lungs. no pleural effusion or pneumothorax. this probably represents pulmonary congestion.\n", "Ground Truth BBox: 56,144,98,198\n", "Predicted Disease: chf\n", "Predicted Report: Report: sternotomy wires. moderate cardiomegaly. small to moderate left pleural effusion with atelectasis. patchy opacity at the right base could represent infection or atelectasis. small right effusion.\n", "Predicted BoundingBoxes: ['306,223,365,300']\n", "------------------------------------------------------------\n", "Row: 55\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/85a3f448-19491fce-f77ce1d9-903c960a-5a0a7f22.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear. normal bones and soft tissues.\n", "Ground Truth BBox: 266,3,318,41\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear. normal bones and soft tissues.\n", "Predicted BoundingBoxes: ['392,28,416,65']\n", "------------------------------------------------------------\n", "Row: 56\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/8c3b4864-b0082cc0-c6b71454-373cab30-a9d65359.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs. lungs are clear. normal bones and soft tissues.\n", "Ground Truth BBox: 59,0,95,26\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['176,194,221,232']\n", "------------------------------------------------------------\n", "Row: 57\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/fa6a4050-e2cd2d80-a772d5b6-bcc74cbf-14f2123e.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: prominent heart. aortic calcifications. hyper-inflated lungs. small bilateral effusions are suspected. no focal consolidation. no pneumothorax.\n", "Ground Truth BBox: 90,108,149,189\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. patchy opacity in the right lower lung. probably atelectasis. no large effusion or pneumothorax.\n", "Predicted BoundingBoxes: ['316,225,374,298']\n", "------------------------------------------------------------\n", "Row: 58\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/97d2bd48-4c000f5c-fbf12147-4a67292b-d5775d2b.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. thoracic spinal degeneration. normal lungs.\n", "Ground Truth BBox: 291,193,333,229\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['205,166,252,224']\n", "------------------------------------------------------------\n", "Row: 59\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/f022416d-f0208897-45208303-37f16738-ae8d1a0e.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 229,72,290,124\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['267,109,314,163']\n", "------------------------------------------------------------\n", "Row: 60\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/b362e24f-2ce327f6-294ab055-a736678f-28ab3f66.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: moderate cardiomegaly. aortic calcifications. no large effusion. prominent pulmonary vessels. patchy right perihilar opacity. this may represent pulmonary congestion.\n", "Ground Truth BBox: 77,131,143,276\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. patchy opacity in the right lung base, could represent atelectasis, infection or edema. there may be a small right effusion.\n", "Predicted BoundingBoxes: ['286,216,326,253']\n", "------------------------------------------------------------\n", "Row: 61\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/48777fa2-80d72d3c-22727ca9-2678db6b-02fa73ff.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: mild cardiomegaly. tortuous aorta. prominent right pulmonary hilum, for which lymphadenopathy and large pulmonary vessels are the primary considerations. there is cephalization vessels with prominence of the smaller pulmonary vessels. increased haziness at the bases possible. probable small bilateral effusions. altogether this probably represents pulmonary edema. no pneumothorax.\n", "Ground Truth BBox: 96,117,345,267\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Predicted BoundingBoxes: ['53,144,121,202']\n", "------------------------------------------------------------\n", "Row: 62\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/777f4e44-1a9924b9-1a753f46-d5f01d62-225dbc23.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear.\n", "Ground Truth BBox: 189,104,233,142\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['168,104,245,168']\n", "------------------------------------------------------------\n", "Row: 63\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/41b99b08-1b9ec92a-def8774b-2b370eb3-57edb2a1.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. low lung volumes. prominent pulmonary vasculature. suspect chronic chf. no acute edema is present.\n", "Ground Truth BBox: 196,109,353,229\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs. prominent pulmonary vessels. kerley b lines on the right. this could represent mild pulmonary edema.\n", "Predicted BoundingBoxes: ['53,161,98,227']\n", "------------------------------------------------------------\n", "Row: 64\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/cd9ac5f8-ecb5d0c1-268d1c67-15fe9467-44310764.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: prominent heart. small bilateral effusions. some band like opacities in the mid and lower lungs bilaterally which could represent kerley b-lines seen in pulmonary edema.\n", "Ground Truth BBox: 66,148,149,235\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. small left effusion with atelectasis. probable trace right effusion as well. the lungs may be hyper-inflated as well. minimal amount of atelectasis in the right lower lung.\n", "Predicted BoundingBoxes: ['201,196,250,231']\n", "------------------------------------------------------------\n", "Row: 65\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/43d90552-c3efe186-d80a2ed9-ed3662e6-9e1727e6.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiomegaly. aortic calcifications. couple rounded opacities in the right lower lung could represent metastatic disease or pneumonia. left lung appears clear.\n", "Ground Truth BBox: 92,171,160,301\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. small left effusion with atelectasis. probable trace right effusion as well. the lungs may be hyper-inflated as well. aortic calcifications.\n", "Predicted BoundingBoxes: ['297,253,358,309']\n", "------------------------------------------------------------\n", "Row: 66\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/b8ba3688-c33f4901-68666539-5ac881b0-5bc5394c.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: prominent heart. lungs are clear.\n", "Ground Truth BBox: 215,138,271,184\n", "Predicted Disease: chf\n", "Predicted Report: Report: mild cardiomegaly. small left effusion with atelectasis. prominent pulmonary vessels. mild haziness at the bases. no focal consolidation. no pneumothorax. sternotomy wires.\n", "Predicted BoundingBoxes: ['339,203,416,271']\n", "------------------------------------------------------------\n", "Row: 67\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/0cf598c5-4b0fa880-f002e739-60e4b993-0346123e.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: moderate cardiomegaly. there is at least moderate left effusion with atelectasis or consolidation. prominent pulmonary vessels. post-surgical changes in the upper mediastinum. sternotomy wires. left-sided cardiac pacer with leads projecting over the right atrium and ventricle.\n", "Ground Truth BBox: 290,176,351,243\n", "Predicted Disease: chf\n", "Predicted Report: Report: moderate cardiomegaly. left-sided cardiac defibrillator with lead projecting over the left ventricle. right costophrenic angle is not included. no large pleural effusion. no pneumothorax. lungs are clear as visualized.\n", "Predicted BoundingBoxes: ['20,182,69,259']\n", "------------------------------------------------------------\n", "Row: 68\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/454378b1-a9a7a9dd-c2590a50-9c74a1a7-3af2d1d8.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: cardiac silhouette is severely enlarged. small bilateral effusions with patchy atelectasis bilaterally. superimposed infection not excluded. there's some density in the left shoulder glenohumeral joint of questionable significance. this could represent a calcified loose body. thoracic spinal degeneration.\n", "Ground Truth BBox: 330,91,390,160\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. small left effusion with atelectasis. probable trace right effusion as well. the lungs may be hyper-inflated as well. aortic calcifications.\n", "Predicted BoundingBoxes: ['297,226,358,272']\n", "------------------------------------------------------------\n", "Row: 69\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/3ac68e75-77571934-ae24d154-f80e05b9-7ff3fd09.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: faint aortic calcifications. mediastinum and heart otherwise normal. patient is rotated. lungs are clear.\n", "Ground Truth BBox: 75,136,142,172\n", "Predicted Disease: normal\n", "Predicted Report: Report: lung apices are not completely included. normal heart and mediastinum. lungs are clear as visualized.\n", "Predicted BoundingBoxes: ['196,0,248,51']\n", "------------------------------------------------------------\n", "Row: 70\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/8e457921-bc1af8aa-a65073c1-aaac8247-c5ceb780.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: sternotomy wires. cardiac valve replacement. left sided pacer with leads projecting over the right atrium and coronary sinus. prominent heart. the lungs are clear. bones and soft tissues normal.\n", "Ground Truth BBox: 72,0,113,23\n", "Predicted Disease: chf\n", "Predicted Report: Report: sternotomy wires. cardiac valve replacement. left sided pacer with leads projecting over the right atrium and ventricle. prominent heart. the lungs are clear. bones and soft tissues normal.\n", "Predicted BoundingBoxes: ['0,38,30,81']\n", "------------------------------------------------------------\n", "Row: 71\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/91e08b73-04b55312-fd8a9d6f-bedbcc79-38d8ab4f.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: left sided cardiac pacer with leads projecting over right atrium and ventricle. cardiomegaly. aortic calcifications. lungs are clear.\n", "Ground Truth BBox: 299,138,362,173\n", "Predicted Disease: chf\n", "Predicted Report: Report: moderate cardiomegaly. left-sided cardiac defibrillator with lead tip not completely included. patchy opacities in the right mid and lower lung could be infectious or atelectasis. suspect mild congestion. right costophrenic angle not completely included. no large effusion or pneumothorax.\n", "Predicted BoundingBoxes: ['31,188,116,292']\n", "------------------------------------------------------------\n", "Row: 72\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/80aad8eb-4d7606d7-7d32f321-3388a97f-a3bfd76f.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: normal heart and mediastinum. streaky scarring or atelectasis at the left lung base. no pleural effusion or pneumothorax.\n", "Ground Truth BBox: 362,282,415,375\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Predicted BoundingBoxes: ['53,271,96,315']\n", "------------------------------------------------------------\n", "Row: 73\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/23526aab-143a5005-a3492444-cf3a3b90-362fd02e.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: costophrenic angle is not included. normal lungs otherwise. heart and mediastinum normal. bones and soft tissues normal.\n", "Ground Truth BBox: 183,130,231,199\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['205,138,252,184']\n", "------------------------------------------------------------\n", "Row: 74\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/b9e1f8ba-fe14fbd4-3d72ef71-a40df34c-c593a140.png\n", "Ground Truth Disease: chf\n", "Ground Truth Report: sternotomy wires. cardiac clips. cardiomegaly. aortic calcifications. prominent pulmonary vessels. patchy opacity at the bases probably represents edema. infection's also possible. there's some irregularity of the right shoulder. thoracic spinal degeneration.\n", "Ground Truth BBox: 20,56,85,130\n", "Predicted Disease: chf\n", "Predicted Report: Report: cardiomegaly. patchy bibasilar opacities, which could represent atelectasis or edema. prominent pulmonary vasculature. no large effusion or pneumothorax.\n", "Predicted BoundingBoxes: ['317,210,362,254']\n", "------------------------------------------------------------\n", "Row: 75\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/f94dbe00-6a2a4944-c1dd5053-ea71b764-f4c5ebb5.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: aortic calcifications. slightly prominent heart. air in the transverse colon. elevated right lung base slightly. lungs are clear.\n", "Ground Truth BBox: 67,278,130,346\n", "Predicted Disease: normal\n", "Predicted Report: Report: normal heart and mediastinum. lungs are clear.\n", "Predicted BoundingBoxes: ['173,106,224,158']\n", "------------------------------------------------------------\n", "Row: 76\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/445fde2d-8f80b5b5-fb567a45-a78ff0da-7a93d16b.png\n", "Ground Truth Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 91,73,156,112\n", "Predicted Disease: normal\n", "Predicted Report: Report: lung apices are not completely included. normal heart and mediastinum. lungs are clear as visualized.\n", "Predicted BoundingBoxes: ['265,122,307,168']\n", "------------------------------------------------------------\n", "\n", "================ METRICS ================\n", "\n", "Accuracy: 0.9474\n", "\n", "Confusion Matrix:\n", "[[38 0]\n", " [ 4 34]]\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " chf 0.9048 1.0000 0.9500 38\n", " normal 1.0000 0.8947 0.9444 38\n", "\n", " accuracy 0.9474 76\n", " macro avg 0.9524 0.9474 0.9472 76\n", "weighted avg 0.9524 0.9474 0.9472 76\n", "\n" ] } ], "source": [ "import pandas as pd\n", "import re\n", "from sklearn.metrics import classification_report, accuracy_score, confusion_matrix\n", "import ast\n", "\n", "# --------------------------------------------------\n", "# CONFIG\n", "# --------------------------------------------------\n", "csv_path = \"/home/shanin/Desktop/SHANIN/EyeGaze/CHEST/MODEL/93_ALL/test.csv\"\n", "\n", "# --------------------------------------------------\n", "# LOAD CSV\n", "# --------------------------------------------------\n", "df = pd.read_csv(csv_path)\n", "\n", "# Sanity checks\n", "assert \"image_path\" in df.columns, \"CSV must have 'image_path'\"\n", "assert \"disease\" in df.columns, \"CSV must have 'disease'\"\n", "assert \"radiology_report\" in df.columns, \"CSV must have 'radiology_report'\"\n", "assert \"heatmap_rescaled_boxes\" in df.columns, \"CSV must have 'heatmap_rescaled_boxes'\"\n", "\n", "# clean predicted disease\n", "def clean_disease(text):\n", " if not isinstance(text, str):\n", " return \"\"\n", " text = text.lower().strip()\n", " prefixes = [\"disease type:\", \"disease:\", \"diagnosis:\"]\n", " for p in prefixes:\n", " if text.startswith(p):\n", " text = text.replace(p, \"\").strip()\n", " return text\n", "\n", "# clean predicted report\n", "def clean_report(text):\n", " if not isinstance(text, str):\n", " return \"\"\n", "\n", " # Remove \"Report:\" label\n", " text = re.sub(r\"(?i)\\breport:\\b\", \"\", text)\n", "\n", " # Remove entire BoundingBoxes line\n", " text = re.sub(r\"(?i)boundingboxes:.*\", \"\", text)\n", "\n", " return text.strip()\n", "\n", "\n", "def extract_bounding_boxes(text):\n", " \"\"\"\n", " Extract all bounding boxes in x1,y1,x2,y2 format\n", " \"\"\"\n", " if not isinstance(text, str):\n", " return []\n", " boxes = re.findall(r\"(.*?)\", text)\n", " return boxes\n", "\n", "def get_highest_conf_gt_bbox(text):\n", " \"\"\"\n", " Parse heatmap_rescaled_boxes column and return\n", " highest-confidence bbox as x1,y1,x2,y2 (string)\n", " \"\"\"\n", " if not isinstance(text, str) or text.strip() == \"\":\n", " return None\n", "\n", " try:\n", " boxes = ast.literal_eval(text) # safely parse list of dicts\n", " if not isinstance(boxes, list) or len(boxes) == 0:\n", " return None\n", "\n", " # pick highest confidence box\n", " best_box = max(boxes, key=lambda x: x.get(\"confidence\", 0))\n", "\n", " return f\"{best_box['x1']},{best_box['y1']},{best_box['x2']},{best_box['y2']}\"\n", "\n", " except Exception:\n", " return None\n", "\n", "\n", "# RUN INFERENCE\n", "y_true = []\n", "y_pred = []\n", "predictions = []\n", "\n", "for idx, row in df.iterrows():\n", " image_path = row[\"image_path\"]\n", " gt_disease = row[\"disease\"].lower().strip()\n", " gt_report = row[\"radiology_report\"]\n", "\n", " # ---- Ground truth bbox (highest confidence only) ----\n", " gt_bbox = get_highest_conf_gt_bbox(row[\"heatmap_rescaled_boxes\"])\n", "\n", " # ---- Model inference ----\n", " pred_text = run_inference(image_path)\n", "\n", " # ---- Parse model output ----\n", " lines = pred_text.split(\"\\n\")\n", "\n", " # Disease\n", " raw_pred_disease = lines[0] if len(lines) > 0 else \"\"\n", " pred_disease = clean_disease(raw_pred_disease)\n", "\n", " # Report\n", " raw_pred_report = \"\\n\".join(lines[1:]) if len(lines) > 1 else \"\"\n", " pred_report = clean_report(raw_pred_report)\n", "\n", " # Predicted bounding boxes\n", " pred_bboxes = extract_bounding_boxes(raw_pred_report)\n", "\n", " # ---- PRINT ----\n", " print(f\"Row: {idx + 1}\")\n", " print(f\"Image: {image_path}\")\n", " print(f\"Ground Truth Disease: {gt_disease}\")\n", " print(f\"Ground Truth Report: {gt_report}\")\n", " print(f\"Ground Truth BBox: {gt_bbox}\")\n", " print(f\"Predicted Disease: {pred_disease}\")\n", " print(f\"Predicted Report: {pred_report}\")\n", " print(f\"Predicted BoundingBoxes: {pred_bboxes}\")\n", " print(\"-\" * 60)\n", "\n", " # ---- Save for evaluation ----\n", " y_true.append(gt_disease)\n", " y_pred.append(pred_disease)\n", "\n", " predictions.append({\n", " \"image_path\": image_path,\n", " \"disease\": gt_disease,\n", " \"radiology_report\": gt_report,\n", " \"gt_bbox\": gt_bbox,\n", " \"pred_disease\": pred_disease,\n", " \"pred_report\": pred_report,\n", " \"pred_bboxes\": pred_bboxes\n", " })\n", "\n", "\n", "# EVALUATION\n", "print(\"\\n================ METRICS ================\\n\")\n", "accuracy = accuracy_score(y_true, y_pred)\n", "print(f\"Accuracy: {accuracy:.4f}\\n\")\n", "\n", "print(\"Confusion Matrix:\")\n", "print(confusion_matrix(y_true, y_pred))\n", "print()\n", "\n", "print(\"Classification Report:\")\n", "print(classification_report(y_true, y_pred, digits=4))" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "===== Image 1 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/116c787f-3423c257-151f5943-ae7bd2ff-b7f0c496.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. patchy bibasilar opacities, which could represent atelectasis or edema. sternotomy wires. left sided cardiac pacer defibrillator with leads in the right atrium ventricle and coronary sinus. right sided lead is also present.\n", "Predicted Report: left sided cardiac pacer with leads projecting over the right atrium and ventricle. prominent heart. aortic calcifications. lungs are clear.\n", "Ground Truth BBox: 118,124,258,336 | Predicted BBox: 150,90,271,258\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 2 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/2c466a34-8db99db4-27bcd765-38a47cbd-3a16cc3e.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: left-sided cardiac defibrillator with lead in the right ventricle. enlarged heart. left costophrenic angle is not included. left lung base is not included. small right effusion is suspected. vague haziness in the right mid lung. probably artifactual but could represent pneumonia.\n", "Predicted Report: left sided cardiac pacer with leads projecting over the right atrium and ventricle. prominent heart. aortic calcifications. lungs are clear.\n", "Ground Truth BBox: 196,139,236,172 | Predicted BBox: 190,106,245,153\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 3 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/958653fa-56af9e10-318e69a7-abaf2cc0-62e382de.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. slightly prominent heart. no pleural effusion. lungs appear normal. no pneumothorax. necklace noted at the neck.\n", "Predicted Report: cardiomegaly. slight haziness at the bases, could be normal or could represent mild congestion. no effusion or pneumothorax.\n", "Ground Truth BBox: 90,219,131,253 | Predicted BBox: 85,189,141,259\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 4 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/291a3ece-3412be54-831054c7-47c35f08-b179cc2f.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. mild thoracic spinal degeneration. lungs are clear. mild cervical spinal degeneration.\n", "Predicted Report: the lungs are clear. normal heart. soft tissues and bones normal.\n", "Ground Truth BBox: 152,113,224,311 | Predicted BBox: 181,113,246,215\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 5 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/b772f053-63468411-84270890-1c3c09b7-ea75dee6.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs. normal bones and soft tissues.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 173,65,359,162 | Predicted BBox: 173,52,224,104\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 6 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/402ec1ad-8a7ec057-bd0d04ec-2db0bbb5-44ebc4ed.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 189,113,240,156 | Predicted BBox: 52,145,115,186\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 7 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/cb1f25ef-87f09c2a-0f656ffe-f63022ab-8b305520.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: prominent heart. low lung volumes. left basilar opacity difficult to determine due to heart position. there may be small bilateral effusions with suspected patchy opacity of both bases.\n", "Predicted Report: mild cardiomegaly. lungs are clear.\n", "Ground Truth BBox: 125,141,178,179 | Predicted BBox: 90,148,150,202\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 8 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/41f4628d-3a6c7bdf-83f3187d-179970df-a99f7a86.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal lungs. no pleural effusion. no pneumothorax. aortic calcifications. normal heart.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 217,117,253,161 | Predicted BBox: 205,77,252,158\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 9 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/a1030f13-afc2d3d2-f194ebd1-e5a24299-0e09321f.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 155,106,223,198 | Predicted BBox: 168,45,228,144\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 10 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/f3a785c1-784233ee-57d4524a-7f26f6b4-f1f8d497.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: lung bases not entirely included. cardiomegaly. hyper-inflated lungs with areas of scarring. patchy opacity in the perihilar and lower lobes bilateral. bilaterally probably edema or infection.\n", "Predicted Report: lung bases are not completely included. cardiomegaly. hyper-inflated lungs with areas of scarring. patchy opacity in the perihilar and lower lobes bilateral. bilaterally probably edema or infection.\n", "Ground Truth BBox: 209,224,345,380 | Predicted BBox: 265,194,304,234\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 11 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/29bdb8bb-bacbe53c-f4a892e6-3cfc384e-bc7b3897.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: sternotomy wires. cardiomegaly. moderate pleural right minor fissure. bilateral effusions right greater than the left with atelectasis or consolidation.\n", "Predicted Report: sternotomy wires. cardiomegaly. generalized opacity at the bases. probably edema. small effusions suspected. there is some fluid in the right minor fissure. aortic valve. prosthesis.\n", "Ground Truth BBox: 308,202,397,271 | Predicted BBox: 350,268,416,329\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 12 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/d570b545-7871b706-67c58c73-3f24d518-5fb7a23d.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: prominent heart. the patient is lordodically positioned. patchy opacity in the right mid lung and at the right base. probably atelectasis or scarring. suspect a pleural plaque at the left base as well as peripherally at the left lateral pleura. thoracic spinal degeneration.\n", "Predicted Report: cardiomegaly. small bilateral effusions with generalized haziness in the lungs. it's compatible with edema. thoracic spinal degeneration. right ac joint arthritis.\n", "Ground Truth BBox: 164,172,215,238 | Predicted BBox: 0,23,54,78\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 13 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/9c091aff-03c78569-de7a251d-f2a35adb-ff89fa02.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. limited evaluation of the lungs due to high contrast technique. no large effusion or pneumothorax.\n", "Predicted Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Ground Truth BBox: 125,0,161,25 | Predicted BBox: 18,250,61,289\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 14 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/02d7845f-0120d2f5-7dd7585d-ba0d6767-e6038823.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear. right lung base is not completely included.\n", "Predicted Report: lungs are clear. no pleural effusion or pneumothorax. normal heart size and mediastinum. no focal consolidation.\n", "Ground Truth BBox: 335,213,377,248 | Predicted BBox: 365,221,410,261\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 15 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/e8bc2bd1-549efb3d-001ba3a3-ece3b4f9-897ba73b.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs, right greater than left. prominent pulmonary vessels. suspect mild congestion or pulmonary edema.\n", "Predicted Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs. prominent pulmonary vessels. kerley b lines on the right. this could represent mild pulmonary edema.\n", "Ground Truth BBox: 83,119,270,235 | Predicted BBox: 53,174,98,224\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 16 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/feefc68a-0a26d0a0-65e4a2a0-b1efc19d-0abcd7d1.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 197,115,234,159 | Predicted BBox: 193,156,238,206\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 17 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/4ff79c8d-fd7de62b-52ffeb40-2fe8ccfc-f12beb41.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: the chin obscures the lung apices. low lung volumes. dense opacity at the bases bilaterally. probably pleural effusion with edema or infection or atelectasis. prominent heart.\n", "Predicted Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Ground Truth BBox: 41,172,236,296 | Predicted BBox: 50,189,128,251\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 18 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/7b2baa0e-0ccd9471-aeb95bf7-c991b526-85690b9d.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 177,154,219,199 | Predicted BBox: 196,178,251,221\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 19 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/16948ae4-b8be1fa1-6b1fa93f-30dcaa87-cb904cd1.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: right lung is not completely included. lungs appear clear. no large effusion or pneumothorax. normal heart and mediastinum.\n", "Predicted Report: lungs are clear. no pleural effusion or pneumothorax. normal heart size and mediastinum. lungs and soft tissues normal.\n", "Ground Truth BBox: 359,214,416,294 | Predicted BBox: 369,214,416,261\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 20 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/efb03b13-c411b791-e39310a3-982c0a38-1100ccc8.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. elevated right lung base may be due to a large effusion. there is some haziness of the lungs suggesting atelectasis. prominent breast shadow at the left, lung base.\n", "Predicted Report: cardiomegaly. slight haziness at the bases, could be normal or could represent mild congestion. no effusion or pneumothorax.\n", "Ground Truth BBox: 65,98,134,190 | Predicted BBox: 90,136,151,258\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 21 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/3158f4e8-6a034072-b052d188-f4f3b37d-561fff8b.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: patchy bibasilar opacity with cardiomegaly. this could represent edema but infection is also a strong consideration. no pleural effusion or pneumothorax.\n", "Predicted Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Ground Truth BBox: 81,189,163,264 | Predicted BBox: 45,89,116,190\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 22 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/cac3fd9e-f85b2b92-f2109fbb-fe266c7e-41fc8c41.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart. normal mediastinum. normal lungs. normal bones and soft tissues.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 252,226,400,284 | Predicted BBox: 316,220,359,257\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 23 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/1e4d4d01-657d797c-f09f7a14-cc14e092-909e66b8.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: normal heart and mediastinum. prominent pulmonary vasculature. no focal consolidation, pleural effusion or pneumothorax.\n", "Predicted Report: prominent heart. small left effusion with atelectasis. probable trace right effusion as well. the lungs show patchy opacity, most pronounced at the right base, which is not specific. probably edema, but infection is possible as well.\n", "Ground Truth BBox: 316,257,352,301 | Predicted BBox: 305,214,387,291\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 24 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/865de6c6-25704eab-a1f495cf-d8d2bdc3-f3e35f36.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs. thoracic spinal degeneration.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 148,75,244,236 | Predicted BBox: 95,208,151,251\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 25 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/46b6d27f-05fc0509-a106934d-8b60e412-be2d97bb.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: elevated right lung base. cardiomegaly. prominent pulmonary vessels. lungs may be congested. no focal consolidation pleural effusion or pneumothorax.\n", "Predicted Report: cardiomegaly. small bilateral effusions with generalized haziness in the lungs. it's compatible with edema. thoracic spinal degeneration. right ac joint arthritis.\n", "Ground Truth BBox: 68,151,200,238 | Predicted BBox: 39,130,111,230\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 26 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/1a3fc5d7-b29579b6-beaf54aa-a7fde4bc-84ed8700.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal lungs. normal heart and mediastinum soft tissues and bones appear normal.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 159,64,243,156 | Predicted BBox: 197,107,275,186\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 27 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/9a177679-9e809e56-552b0650-230b9dc0-ee2f5a9c.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart questionable midlung opacity of the lower hemithorax could represent a hiatal hernia. the lungs are clear.\n", "Predicted Report: lung apices not completely included. normal heart and mediastinum. lungs are clear as visualized.\n", "Ground Truth BBox: 112,70,156,107 | Predicted BBox: 142,0,179,31\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 28 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/7fd82f55-aaba4935-f5b31bae-0288291b-82128657.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear. normal bones and soft tissues.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 166,127,229,217 | Predicted BBox: 163,106,225,160\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 29 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/955211b8-735186c6-69e732c9-36206c53-a584f3eb.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. patchy opacity bilaterally at the bases. kerley b lines at the left lung base. small effusion suspected. this is the appearance of pulmonary edema.\n", "Predicted Report: cardiomegaly. small left effusion with atelectasis. probable trace right effusion as well. the lungs may be hyper-inflated as well. aortic calcifications.\n", "Ground Truth BBox: 1,207,151,330 | Predicted BBox: 37,230,116,269\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 30 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/c3a8a376-a4621465-bb65ba5d-d8dd3daa-e3e005eb.png\n", "Ground Truth Disease: normal | Predicted Disease: chf\n", "Ground Truth Report: normal heart and mediastinum. patchy atelectasis at the bases.\n", "Predicted Report: cardiomegaly. slight haziness at the bases, could be normal or could represent mild congestion. no effusion or pneumothorax.\n", "Ground Truth BBox: 342,274,377,315 | Predicted BBox: 358,260,416,339\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 31 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/9d9cf045-134d30f9-ffba3d5f-3a145094-80569824.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: prominent heart. prominent perihilar opacity. mediastinum is normal.\n", "Predicted Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Ground Truth BBox: 218,35,288,162 | Predicted BBox: 197,99,244,146\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 32 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/6bcb54fc-797bee0c-5d0b72b7-4b4c2763-e3deef1e.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiac clips. sternotomy wires. prominent heart. aortic calcifications. questionable right infrahilar opacity could be artifactual or could represent atelectasis or early infiltrate.\n", "Predicted Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Ground Truth BBox: 70,188,130,291 | Predicted BBox: 357,293,416,338\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 33 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/689f0cd0-ee982281-95438dd2-a6b493b7-d50387b7.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: normal heart and mediastinum. aortic calcifications. normal lungs.\n", "Predicted Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Ground Truth BBox: 196,99,262,146 | Predicted BBox: 317,226,360,262\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 34 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/e04f3597-e6cdfe8d-68111116-ad5c5cfd-30ac5867.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: lungs are clear. sternotomy wires. normal heart size. aortic calcifications.\n", "Predicted Report: lungs are clear. no pleural effusion or pneumothorax. normal heart.\n", "Ground Truth BBox: 171,53,273,165 | Predicted BBox: 328,225,370,261\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 35 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/2b98791e-59dca4a7-d62cd907-a81f3bf8-3fe8cd44.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: normal heart. hazy opacity over the lower lungs bilaterally. lungs may be hyper-inflated. suspect pulmonary congestion. no pleural effusion or pneumothorax.\n", "Predicted Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs. prominent pulmonary vessels. kerley b lines on the right. this could represent mild pulmonary edema.\n", "Ground Truth BBox: 16,161,218,325 | Predicted BBox: 53,156,98,202\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 36 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/5c405cb5-414df3fd-57a04c46-8d9c7771-612e2672.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: right sided chest port with its tip in the superior vena cava. normal heart. aortic calcifications. thoracic spinal degeneration. lungs are clear.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 77,126,260,335 | Predicted BBox: 205,96,252,158\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 37 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/f716ed09-e6c2f65e-1212e3be-7e8cc983-f9633985.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 197,59,244,120 | Predicted BBox: 193,106,238,144\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 38 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/2ffee6f3-02abd58a-f1c78e0f-7689bf17-f69ea741.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. part of the right heart border is obscured by right sided pleural effusion with atelectasis or consolidation. small amount of fluid in the right minor fissure. reticulonodular opacities throughout the lung apices bilaterally could represent fibrosis or chronic infectious process. no pneumothorax.\n", "Predicted Report: cardiomegaly. aortic calcifications. patchy opacity in the right lung base, could represent atelectasis, infection or edema. there may be a small right effusion.\n", "Ground Truth BBox: 321,244,361,277 | Predicted BBox: 312,216,381,300\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 39 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/669e6e09-9072a04c-c8f9766f-6c877cb6-01239dfd.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs. normal bones and soft tissues.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 196,20,303,216 | Predicted BBox: 193,106,240,142\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 40 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/24c7496c-d7635dfe-b8e0b87f-d818affc-78ff7cf4.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: mild cardiomegaly. generalized haziness of lungs with basilar predominance. no large effusion. this likely represents mild edema.\n", "Predicted Report: cardiomegaly. generalized perihilar density bilaterally, which could represent edema or congestion. questionable small amount of fluid in the right minor fissure. tiny right left effusion is difficult to exclude. no large pleural effusion. thoracic spinal degeneration.\n", "Ground Truth BBox: 68,182,151,308 | Predicted BBox: 84,176,135,234\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 41 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/655ca63b-91739e04-2121ab41-bb8734f9-d8fcd64b.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear.\n", "Predicted Report: normal heart. aortic calcifications. lungs are clear.\n", "Ground Truth BBox: 213,120,262,173 | Predicted BBox: 223,106,276,158\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 42 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/21fc8b35-43aaab0e-db4630fd-8ecebbb4-6eba92e6.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: low lung volumes. prominent heart. band of atelectasis at the right base. no pleural effusion or pneumothorax.\n", "Predicted Report: prominent heart. lungs are clear.\n", "Ground Truth BBox: 194,103,235,139 | Predicted BBox: 178,104,245,165\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 43 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/41183cc7-29fa548f-28a3348b-7ab3dfc8-162c2882.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: right lung base is not entirely included. normal lungs. no left pleural effusion. no pneumothorax. normal heart. bones and soft tissues appear normal.\n", "Predicted Report: lung apices not completely included. normal heart and mediastinum. lungs are clear as visualized.\n", "Ground Truth BBox: 131,23,195,98 | Predicted BBox: 163,0,202,51\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 44 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/80b49786-88a74899-70e7ecab-98cc7ca9-261155eb.png\n", "Ground Truth Disease: normal | Predicted Disease: chf\n", "Ground Truth Report: prominent heart. elevated right lung base. there may be a small left effusion. no, focal consolidation. no pneumothorax.\n", "Predicted Report: cardiomegaly. aortic calcifications. thoracic spinal degeneration. lungs are clear.\n", "Ground Truth BBox: 116,160,175,218 | Predicted BBox: 87,158,149,262\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 45 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/ea543c1f-a2c5721c-d49e3110-946dde27-06a1f23f.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. aortic calcifications. haziness at the bases bilaterally. suspect small left effusion. kerley b lines on the right. prominent pulmonary vasculature. suspect pulmonary edema.\n", "Predicted Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs. prominent pulmonary vessels. kerley b lines on the right. this could represent mild pulmonary edema.\n", "Ground Truth BBox: 318,289,362,326 | Predicted BBox: 44,23,84,79\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 46 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/07e1e6bf-1d6d9740-10f021c0-0a8229f8-2297c5ef.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. left lung is not completely included. no large effusion. lungs are clear as visualized. no pneumothorax. minimal thoracic spinal degeneration.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 219,70,304,127 | Predicted BBox: 209,104,253,141\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 47 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/27d78392-c6742897-792df26a-12210f36-65052f2f.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: severe cardiomegaly. patchy opacity in the right infrahilar region. could represent edema or atelectasis or pneumonia. left lung base is obscured by the heart\n", "Predicted Report: cardiomegaly. aortic calcifications. patchy opacity in the right lung base, could represent atelectasis, infection or edema. there may be a small right effusion.\n", "Ground Truth BBox: 256,177,380,245 | Predicted BBox: 297,194,358,231\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 48 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/3585208b-6a11bfad-bea7b95e-71894d45-ce2303f5.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear. thoracic spinal degeneration.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 208,121,249,155 | Predicted BBox: 193,154,238,193\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 49 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/257c9f52-0f0c9004-994dbd15-522a597e-912b68fa.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 199,68,275,215 | Predicted BBox: 193,68,238,181\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 50 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/33ca3ff6-93eeef9a-924a08de-e2b8309a-b757adfa.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: mild cardiomegaly. patchy perihilar opacity bilaterally could represent mild edema or infection. right costophrenic angle is not completely included. left costrophrenic angle is not completely included. there is a nonspecific metallic density projecting in the right cardiophrenic angle.\n", "Predicted Report: mild cardiomegaly. patchy perihilar opacity bilaterally could represent mild edema or infection. right costophrenic angle is not completely included. left costrophrenic angle is not completely included. there is a nodule or a calcification in the left upper lung. no pneumothorax.\n", "Ground Truth BBox: 81,130,182,282 | Predicted BBox: 207,199,250,260\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 51 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/62f2a462-83750eca-c384d41e-51503453-7459f59d.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: enlarged heart. aortic calcifications. lungs are clear. no pleural effusion or pneumothorax.\n", "Predicted Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Ground Truth BBox: 208,84,244,127 | Predicted BBox: 171,97,213,146\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 52 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/82f43a3b-f8b67cde-6ea58061-6f145d11-266b9f40.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear. no pleural effusion or pneumothorax. bones and soft tissues normal.\n", "Predicted Report: normal heart. aortic calcifications. lungs are clear.\n", "Ground Truth BBox: 196,136,240,172 | Predicted BBox: 201,106,256,181\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 53 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/0f502a52-7d8fb5f0-91fd0fa6-39f88d77-b6f57c7f.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal lungs. aortic calcifications. normal heart.\n", "Predicted Report: prominent heart. low lung volumes. no focal consolidation, pleural effusion or pneumothorax.\n", "Ground Truth BBox: 50,92,93,128 | Predicted BBox: 90,48,137,147\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 54 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/0b79395e-dccedfe8-af5b2694-f13872f0-516e4c8b.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: sternotomy wires. left-sided cardiac pacer with leads projecting over the right atrium and ventricle. cardiomegaly. prominent pulmonary vessels. mild haziness of the lungs. no pleural effusion or pneumothorax. this probably represents pulmonary congestion.\n", "Predicted Report: sternotomy wires. moderate cardiomegaly. small to moderate left pleural effusion with atelectasis. patchy opacity at the right base could represent infection or edema. prominent pulmonary vasculature. small right effusion is suspected. this could represent pulmonary edema.\n", "Ground Truth BBox: 30,112,347,331 | Predicted BBox: 290,176,365,233\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 55 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/85a3f448-19491fce-f77ce1d9-903c960a-5a0a7f22.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear. normal bones and soft tissues.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 169,56,230,128 | Predicted BBox: 193,106,258,158\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 56 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/8c3b4864-b0082cc0-c6b71454-373cab30-a9d65359.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. normal lungs. lungs are clear. normal bones and soft tissues.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 161,183,196,225 | Predicted BBox: 176,194,221,232\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 57 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/fa6a4050-e2cd2d80-a772d5b6-bcc74cbf-14f2123e.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: prominent heart. aortic calcifications. hyper-inflated lungs. small bilateral effusions are suspected. no focal consolidation. no pneumothorax.\n", "Predicted Report: cardiomegaly. aortic calcifications. patchy opacity in the right lower lung. probably atelectasis. no large effusion or pneumothorax.\n", "Ground Truth BBox: 291,206,351,274 | Predicted BBox: 316,225,374,298\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 58 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/97d2bd48-4c000f5c-fbf12147-4a67292b-d5775d2b.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. thoracic spinal degeneration. normal lungs.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 146,125,234,228 | Predicted BBox: 205,166,252,224\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 59 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/f022416d-f0208897-45208303-37f16738-ae8d1a0e.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 234,131,275,165 | Predicted BBox: 267,109,314,163\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 60 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/b362e24f-2ce327f6-294ab055-a736678f-28ab3f66.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: moderate cardiomegaly. aortic calcifications. no large effusion. prominent pulmonary vessels. patchy right perihilar opacity. this may represent pulmonary congestion.\n", "Predicted Report: cardiomegaly. aortic calcifications. patchy opacity in the right lung base, could represent atelectasis, infection or edema. there may be a small right effusion.\n", "Ground Truth BBox: 236,142,300,230 | Predicted BBox: 286,216,326,253\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 61 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/48777fa2-80d72d3c-22727ca9-2678db6b-02fa73ff.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: mild cardiomegaly. tortuous aorta. prominent right pulmonary hilum, for which lymphadenopathy and large pulmonary vessels are the primary considerations. there is cephalization vessels with prominence of the smaller pulmonary vessels. increased haziness at the bases possible. probable small bilateral effusions. altogether this probably represents pulmonary edema. no pneumothorax.\n", "Predicted Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Ground Truth BBox: 96,117,345,267 | Predicted BBox: 53,144,121,202\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 62 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/777f4e44-1a9924b9-1a753f46-d5f01d62-225dbc23.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. the lungs are clear.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 189,104,233,142 | Predicted BBox: 168,104,228,168\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 63 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/41b99b08-1b9ec92a-def8774b-2b370eb3-57edb2a1.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. low lung volumes. prominent pulmonary vasculature. suspect chronic chf. no acute edema is present.\n", "Predicted Report: cardiomegaly. aortic calcifications. generalized haziness of the lungs. prominent pulmonary vessels. kerley b lines on the right. this could represent mild pulmonary edema.\n", "Ground Truth BBox: 75,158,184,276 | Predicted BBox: 53,161,98,227\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 64 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/cd9ac5f8-ecb5d0c1-268d1c67-15fe9467-44310764.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: prominent heart. small bilateral effusions. some band like opacities in the mid and lower lungs bilaterally which could represent kerley b-lines seen in pulmonary edema.\n", "Predicted Report: moderate cardiomegaly. small left effusion with atelectasis. trace right effusion is suspected as well. lungs are otherwise clear.\n", "Ground Truth BBox: 66,148,149,235 | Predicted BBox: 322,230,365,269\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 65 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/43d90552-c3efe186-d80a2ed9-ed3662e6-9e1727e6.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiomegaly. aortic calcifications. couple rounded opacities in the right lower lung could represent metastatic disease or pneumonia. left lung appears clear.\n", "Predicted Report: cardiomegaly. small left effusion with atelectasis. probable trace right effusion as well. the lungs may be hyper-inflated as well. aortic calcifications.\n", "Ground Truth BBox: 296,191,342,288 | Predicted BBox: 297,253,358,309\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 66 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/b8ba3688-c33f4901-68666539-5ac881b0-5bc5394c.png\n", "Ground Truth Disease: normal | Predicted Disease: chf\n", "Ground Truth Report: prominent heart. lungs are clear.\n", "Predicted Report: mild cardiomegaly. small left effusion with atelectasis. prominent pulmonary vessels. mild haziness at the bases. no focal consolidation. no pneumothorax. sternotomy wires.\n", "Ground Truth BBox: 215,138,271,184 | Predicted BBox: 339,203,416,271\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 67 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/0cf598c5-4b0fa880-f002e739-60e4b993-0346123e.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: moderate cardiomegaly. there is at least moderate left effusion with atelectasis or consolidation. prominent pulmonary vessels. post-surgical changes in the upper mediastinum. sternotomy wires. left-sided cardiac pacer with leads projecting over the right atrium and ventricle.\n", "Predicted Report: moderate cardiomegaly. left-sided cardiac defibrillator with lead projecting over the left ventricle. right costophrenic angle is not included. no large pleural effusion. no pneumothorax. lungs are clear as visualized.\n", "Ground Truth BBox: 67,204,107,237 | Predicted BBox: 20,182,69,259\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 68 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/454378b1-a9a7a9dd-c2590a50-9c74a1a7-3af2d1d8.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: cardiac silhouette is severely enlarged. small bilateral effusions with patchy atelectasis bilaterally. superimposed infection not excluded. there's some density in the left shoulder glenohumeral joint of questionable significance. this could represent a calcified loose body. thoracic spinal degeneration.\n", "Predicted Report: cardiomegaly. small left effusion with atelectasis. probable trace right effusion as well. the lungs may be hyper-inflated as well. aortic calcifications.\n", "Ground Truth BBox: 253,175,335,282 | Predicted BBox: 297,226,358,272\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 69 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/3ac68e75-77571934-ae24d154-f80e05b9-7ff3fd09.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: faint aortic calcifications. mediastinum and heart otherwise normal. patient is rotated. lungs are clear.\n", "Predicted Report: lung apices are not completely included. normal heart and mediastinum. lungs are clear as visualized.\n", "Ground Truth BBox: 196,41,351,169 | Predicted BBox: 196,0,248,51\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 70 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/8e457921-bc1af8aa-a65073c1-aaac8247-c5ceb780.png\n", "Ground Truth Disease: chf | Predicted Disease: normal\n", "Ground Truth Report: sternotomy wires. cardiac valve replacement. left sided pacer with leads projecting over the right atrium and coronary sinus. prominent heart. the lungs are clear. bones and soft tissues normal.\n", "Predicted Report: left sided cardiac pacer with leads projecting over the right atrium and ventricle. normal heart size. lungs are clear. no pleural effusion or pneumothorax.\n", "Ground Truth BBox: 162,142,346,244 | Predicted BBox: 307,199,350,236\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 71 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/91e08b73-04b55312-fd8a9d6f-bedbcc79-38d8ab4f.png\n", "Ground Truth Disease: normal | Predicted Disease: chf\n", "Ground Truth Report: left sided cardiac pacer with leads projecting over right atrium and ventricle. cardiomegaly. aortic calcifications. lungs are clear.\n", "Predicted Report: moderate cardiomegaly. left-sided cardiac defibrillator with lead tip not completely included. patchy opacities in the right mid and lower lung could be infectious or atelectasis. suspect mild congestion. right costophrenic angle not completely included. no large effusion or pneumothorax.\n", "Ground Truth BBox: 76,206,117,241 | Predicted BBox: 31,188,116,292\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 72 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/80aad8eb-4d7606d7-7d32f321-3388a97f-a3bfd76f.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: normal heart and mediastinum. streaky scarring or atelectasis at the left lung base. no pleural effusion or pneumothorax.\n", "Predicted Report: cardiomegaly. prominent pulmonary vasculature. mild generalized haziness of lungs. suspect kerley b lines on the left. no large effusion.\n", "Ground Truth BBox: 55,251,89,292 | Predicted BBox: 53,271,96,315\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 73 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/23526aab-143a5005-a3492444-cf3a3b90-362fd02e.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: costophrenic angle is not included. normal lungs otherwise. heart and mediastinum normal. bones and soft tissues normal.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 183,130,231,199 | Predicted BBox: 205,138,252,184\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 74 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/b9e1f8ba-fe14fbd4-3d72ef71-a40df34c-c593a140.png\n", "Ground Truth Disease: chf | Predicted Disease: chf\n", "Ground Truth Report: sternotomy wires. cardiac clips. cardiomegaly. aortic calcifications. prominent pulmonary vessels. patchy opacity at the bases probably represents edema. infection's also possible. there's some irregularity of the right shoulder. thoracic spinal degeneration.\n", "Predicted Report: cardiomegaly. patchy peri-infrahilar opacity bilaterally. small effusions bilaterally. suspect a background of copd.\n", "Ground Truth BBox: 316,216,366,263 | Predicted BBox: 317,225,362,270\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 75 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/f94dbe00-6a2a4944-c1dd5053-ea71b764-f4c5ebb5.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: aortic calcifications. slightly prominent heart. air in the transverse colon. elevated right lung base slightly. lungs are clear.\n", "Predicted Report: normal heart and mediastinum. lungs are clear.\n", "Ground Truth BBox: 186,86,262,161 | Predicted BBox: 173,106,224,158\n", "\n", "--------------------------------------------------------------------------------\n", "===== Image 76 / 76 =====\n", "Image: /home/shanin/Desktop/SHANIN/EyeGaze/Dataset/EGD-MIMIC-JPG-416-AUG/445fde2d-8f80b5b5-fb567a45-a78ff0da-7a93d16b.png\n", "Ground Truth Disease: normal | Predicted Disease: normal\n", "Ground Truth Report: normal heart and mediastinum. lungs are clear.\n", "Predicted Report: lung apices are not completely included. normal heart and mediastinum. lungs are clear as visualized.\n", "Ground Truth BBox: 91,73,156,112 | Predicted BBox: 265,122,307,168\n", "\n", "--------------------------------------------------------------------------------\n", "\n", "✅ Final combined CSV saved to: /home/shanin/Desktop/SHANIN/EyeGaze/CHEST/MODEL/93_ALL/final_combined_results.csv\n", "\n", "================ METRICS ================\n", "\n", "Accuracy: 0.9342\n", "\n", "Confusion Matrix:\n", "[[37 1]\n", " [ 4 34]]\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " chf 0.9024 0.9737 0.9367 38\n", " normal 0.9714 0.8947 0.9315 38\n", "\n", " accuracy 0.9342 76\n", " macro avg 0.9369 0.9342 0.9341 76\n", "weighted avg 0.9369 0.9342 0.9341 76\n", "\n" ] } ], "source": [ "import pandas as pd\n", "import re\n", "from sklearn.metrics import classification_report, accuracy_score, confusion_matrix\n", "import ast\n", "\n", "# --------------------------------------------------\n", "# CONFIG\n", "# --------------------------------------------------\n", "csv_path = \"/home/shanin/Desktop/SHANIN/EyeGaze/CHEST/MODEL/93_ALL/test.csv\"\n", "final_csv_path = \"/home/shanin/Desktop/SHANIN/EyeGaze/CHEST/MODEL/93_ALL/final_combined_results.csv\"\n", "\n", "# --------------------------------------------------\n", "# LOAD CSV\n", "# --------------------------------------------------\n", "df = pd.read_csv(csv_path)\n", "\n", "# Sanity checks\n", "assert \"image_path\" in df.columns, \"CSV must have 'image_path'\"\n", "assert \"disease\" in df.columns, \"CSV must have 'disease'\"\n", "assert \"radiology_report\" in df.columns, \"CSV must have 'radiology_report'\"\n", "assert \"heatmap_rescaled_boxes\" in df.columns, \"CSV must have 'heatmap_rescaled_boxes'\"\n", "\n", "# --------------------------------------------------\n", "# HELPER FUNCTIONS\n", "# --------------------------------------------------\n", "def clean_disease(text):\n", " if not isinstance(text, str):\n", " return \"\"\n", " text = text.lower().strip()\n", " prefixes = [\"disease type:\", \"disease:\", \"diagnosis:\"]\n", " for p in prefixes:\n", " if text.startswith(p):\n", " text = text.replace(p, \"\").strip()\n", " return text\n", "\n", "def clean_report(text):\n", " if not isinstance(text, str):\n", " return \"\"\n", " text = re.sub(r\"(?i)^\\s*report\\s*:\\s*\", \"\", text)\n", " text = re.sub(r\"(?i)\\s*boundingboxes\\s*:.*$\", \"\", text, flags=re.MULTILINE)\n", " text = re.sub(r\"(?i)boundingboxes\\s*:.*\", \"\", text)\n", " return text.strip()\n", "\n", "def extract_bounding_boxes(text):\n", " if not isinstance(text, str):\n", " return []\n", " boxes = re.findall(r\"(.*?)\", text)\n", " return boxes\n", "\n", "def bbox_iou(boxA, boxB):\n", " xA = max(boxA[0], boxB[0])\n", " yA = max(boxA[1], boxB[1])\n", " xB = min(boxA[2], boxB[2])\n", " yB = min(boxA[3], boxB[3])\n", "\n", " interWidth = max(0, xB - xA)\n", " interHeight = max(0, yB - yA)\n", " interArea = interWidth * interHeight\n", "\n", " boxAArea = max(0, (boxA[2] - boxA[0])) * max(0, (boxA[3] - boxA[1]))\n", " boxBArea = max(0, (boxB[2] - boxB[0])) * max(0, (boxB[3] - boxB[1]))\n", "\n", " denom = boxAArea + boxBArea - interArea\n", " if denom == 0:\n", " return 0.0\n", " return interArea / float(denom)\n", "\n", "def parse_gt_boxes(text):\n", " try:\n", " boxes = ast.literal_eval(text)\n", " return [\n", " (int(b['x1']), int(b['y1']), int(b['x2']), int(b['y2']))\n", " for b in boxes if isinstance(b, dict)\n", " ]\n", " except Exception:\n", " return []\n", "\n", "def parse_pred_boxes(pred_bboxes):\n", " boxes = []\n", " for b in pred_bboxes:\n", " try:\n", " x1, y1, x2, y2 = map(int, b.split(\",\"))\n", " boxes.append((x1, y1, x2, y2))\n", " except Exception:\n", " continue\n", " return boxes\n", "\n", "# --------------------------------------------------\n", "# RUN INFERENCE & PRINT PER IMAGE\n", "# --------------------------------------------------\n", "y_true = []\n", "y_pred = []\n", "predictions = []\n", "\n", "for idx, row in df.iterrows():\n", " image_path = row[\"image_path\"]\n", " gt_disease = row[\"disease\"].lower().strip()\n", " gt_report = row[\"radiology_report\"]\n", "\n", " # ---- Model inference ----\n", " pred_text = run_inference(image_path) # your inference function\n", "\n", " lines = pred_text.split(\"\\n\")\n", "\n", " # Disease\n", " raw_pred_disease = lines[0] if len(lines) > 0 else \"\"\n", " pred_disease = clean_disease(raw_pred_disease)\n", "\n", " # Report\n", " raw_pred_report = \"\\n\".join(lines[1:]) if len(lines) > 1 else \"\"\n", " pred_report = clean_report(raw_pred_report)\n", "\n", " # Predicted bounding boxes\n", " pred_bboxes = extract_bounding_boxes(raw_pred_report)\n", "\n", " # Save for later CSV\n", " predictions.append({\n", " \"image_path\": image_path,\n", " \"disease\": gt_disease,\n", " \"radiology_report\": gt_report,\n", " \"pred_disease\": pred_disease,\n", " \"pred_report\": pred_report,\n", " \"pred_bboxes\": pred_bboxes\n", " })\n", "\n", " # Disease metrics\n", " y_true.append(gt_disease)\n", " y_pred.append(pred_disease)\n", "\n", " # --------------------------------------------------\n", " # COMPUTE BEST BBOX AND IOU FOR THIS IMAGE\n", " # --------------------------------------------------\n", " gt_boxes = parse_gt_boxes(row['heatmap_rescaled_boxes'])\n", " pred_boxes = parse_pred_boxes(pred_bboxes)\n", "\n", " best_iou = None\n", " best_gt = None\n", " best_pred = None\n", "\n", " if gt_boxes and pred_boxes:\n", " for pred in pred_boxes:\n", " for gt in gt_boxes:\n", " iou = bbox_iou(gt, pred)\n", " if best_iou is None or iou > best_iou:\n", " best_iou = iou\n", " best_gt = gt\n", " best_pred = pred\n", "\n", " if best_gt is None and gt_boxes:\n", " best_gt = gt_boxes[0]\n", "\n", " if best_pred is None and pred_boxes:\n", " best_pred = pred_boxes[0]\n", "\n", " if best_iou is None:\n", " best_iou = 0.0\n", "\n", " gt_bbox_str = f\"{best_gt[0]},{best_gt[1]},{best_gt[2]},{best_gt[3]}\" if best_gt else \"\"\n", " pred_bbox_str = f\"{best_pred[0]},{best_pred[1]},{best_pred[2]},{best_pred[3]}\" if best_pred else \"\"\n", "\n", " # --------------------------------------------------\n", " # PRINT IMMEDIATELY (NO EXTRA NEW LINES)\n", " # --------------------------------------------------\n", " print(\n", " f\"===== Image {idx + 1} / {len(df)} =====\\n\"\n", " f\"Image: {image_path}\\n\"\n", " f\"Ground Truth Disease: {gt_disease} | Predicted Disease: {pred_disease}\\n\"\n", " f\"Ground Truth Report: {gt_report}\\n\"\n", " f\"Predicted Report: {pred_report}\\n\"\n", " f\"Ground Truth BBox: {gt_bbox_str} | Predicted BBox: {pred_bbox_str}\\n\"\n", " )\n", " print(\"-\" * 80)\n", "\n", "\n", "# --------------------------------------------------\n", "# BUILD SINGLE COMBINED CSV\n", "# --------------------------------------------------\n", "combined_rows = []\n", "\n", "for row in predictions:\n", " image_path = row[\"image_path\"]\n", "\n", " gt_boxes = parse_gt_boxes(df.loc[df['image_path'] == image_path, 'heatmap_rescaled_boxes'].values[0])\n", " pred_boxes = parse_pred_boxes(row[\"pred_bboxes\"])\n", "\n", " best_iou = None\n", " best_gt = None\n", " best_pred = None\n", "\n", " if gt_boxes and pred_boxes:\n", " for pred in pred_boxes:\n", " for gt in gt_boxes:\n", " iou = bbox_iou(gt, pred)\n", " if best_iou is None or iou > best_iou:\n", " best_iou = iou\n", " best_gt = gt\n", " best_pred = pred\n", "\n", " if best_gt is None and gt_boxes:\n", " best_gt = gt_boxes[0]\n", " if best_pred is None and pred_boxes:\n", " best_pred = pred_boxes[0]\n", " if best_iou is None:\n", " best_iou = 0.0\n", "\n", " gt_bbox_str = f\"{best_gt[0]},{best_gt[1]},{best_gt[2]},{best_gt[3]}\" if best_gt else \"\"\n", " pred_bbox_str = f\"{best_pred[0]},{best_pred[1]},{best_pred[2]},{best_pred[3]}\" if best_pred else \"\"\n", "\n", " combined_rows.append({\n", " \"image_path\": image_path,\n", " \"ground_truth_disease\": row[\"disease\"],\n", " \"predicted_disease\": row[\"pred_disease\"],\n", " \"ground_truth_report\": row[\"radiology_report\"],\n", " \"predicted_report\": row[\"pred_report\"],\n", " \"gt_bbox\": gt_bbox_str,\n", " \"predicted_bbox\": pred_bbox_str,\n", " \"iou\": round(best_iou,4),\n", " \"num_gt_boxes\": len(gt_boxes),\n", " \"num_pred_boxes\": len(pred_boxes)\n", " })\n", "\n", "# --------------------------------------------------\n", "# SAVE CSV\n", "# --------------------------------------------------\n", "combined_df = pd.DataFrame(combined_rows)\n", "combined_df.to_csv(final_csv_path, index=False, quoting=0)\n", "print(f\"\\n✅ Final combined CSV saved to: {final_csv_path}\")\n", "\n", "# --------------------------------------------------\n", "# EVALUATION\n", "# --------------------------------------------------\n", "print(\"\\n================ METRICS ================\\n\")\n", "accuracy = accuracy_score(y_true, y_pred)\n", "print(f\"Accuracy: {accuracy:.4f}\\n\")\n", "\n", "print(\"Confusion Matrix:\")\n", "print(confusion_matrix(y_true, y_pred))\n", "print()\n", "\n", "print(\"Classification Report:\")\n", "print(classification_report(y_true, y_pred, digits=4))\n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Using device: cuda\n", "Computing OVERALL metrics...\n", "Using device: cuda:0\n", "Using device: cuda:0\n", "Using device: cuda:0\n", "\n", "================ FINAL METRICS TABLE ================\n", "+--------+---------+----------+---------+----------+-----------+-------------+--------+--------+--------+--------+--------+--------+--------------+--------+\n", "| Class | Samples | Mean_IoU | mAP@0.5 | mAP@0.75 | Entity_F1 | Relation_F1 | ROUGE1 | ROUGE2 | ROUGEL | BLEU | METEOR | CIDEr | BERTScore_F1 | CheX_0 |\n", "+--------+---------+----------+---------+----------+-----------+-------------+--------+--------+--------+--------+--------+--------+--------------+--------+\n", "| ALL | 76 | 0.1509 | 0.0132 | 0.0 | 0.4043 | 0.0 | 0.4495 | 0.2692 | 0.4006 | 0.22 | 0.3985 | 1.3037 | 0.8859 | 0.5526 |\n", "| chf | 38 | 0.1323 | 0.0263 | 0.0 | 0.3134 | 0.0 | 0.3405 | 0.1397 | 0.2811 | 0.1331 | 0.3157 | 0.7876 | 0.8629 | 0.2895 |\n", "| normal | 38 | 0.1696 | 0.0 | 0.0 | 0.5666 | 0.0 | 0.5586 | 0.3987 | 0.5201 | 0.3068 | 0.4812 | 1.4445 | 0.9089 | 0.8158 |\n", "+--------+---------+----------+---------+----------+-----------+-------------+--------+--------+--------+--------+--------+--------+--------------+--------+\n" ] } ], "source": [ "import pandas as pd\n", "import torch\n", "import nltk\n", "from tqdm import tqdm\n", "from tabulate import tabulate\n", "\n", "# -----------------------------\n", "# Detection helpers\n", "# -----------------------------\n", "def parse_bbox(bbox_str):\n", " if not isinstance(bbox_str, str):\n", " return None\n", " try:\n", " return tuple(map(int, bbox_str.split(\",\")))\n", " except:\n", " return None\n", "\n", "def compute_iou(boxA, boxB):\n", " if boxA is None or boxB is None:\n", " return 0.0\n", " xA = max(boxA[0], boxB[0])\n", " yA = max(boxA[1], boxB[1])\n", " xB = min(boxA[2], boxB[2])\n", " yB = min(boxA[3], boxB[3])\n", " inter_w = max(0, xB - xA)\n", " inter_h = max(0, yB - yA)\n", " inter_area = inter_w * inter_h\n", " areaA = max(0, boxA[2]-boxA[0]) * max(0, boxA[3]-boxA[1])\n", " areaB = max(0, boxB[2]-boxB[0]) * max(0, boxB[3]-boxB[1])\n", " union_area = areaA + areaB - inter_area\n", " if union_area == 0:\n", " return 0.0\n", " return inter_area / union_area\n", "\n", "# -----------------------------\n", "# NLP / Radiology Metrics\n", "# -----------------------------\n", "from radgraph import RadGraph\n", "from f1chexbert import F1CheXbert\n", "from nltk.translate.bleu_score import sentence_bleu, SmoothingFunction\n", "from nltk.translate.meteor_score import meteor_score\n", "from rouge_score import rouge_scorer\n", "from bert_score import score as bert_score\n", "from pycocoevalcap.cider.cider import Cider\n", "\n", "nltk.download('punkt', quiet=True)\n", "nltk.download('wordnet', quiet=True)\n", "nltk.download('omw-1.4', quiet=True)\n", "\n", "# -----------------------------\n", "# CIDEr wrapper\n", "# -----------------------------\n", "class CIDErMetric:\n", " def __init__(self):\n", " self.cider_scorer = Cider()\n", " def score(self, references, hypotheses):\n", " refs_dict = {i:[r] for i,r in enumerate(references)}\n", " hyps_dict = {i:[h] for i,h in enumerate(hypotheses)}\n", " score, scores_per_sample = self.cider_scorer.compute_score(refs_dict, hyps_dict)\n", " return {\"CIDEr\": score, \"CIDEr_per_sample\": scores_per_sample}\n", "\n", "# -----------------------------\n", "# RadGraph wrapper\n", "# -----------------------------\n", "class RadGraphF1:\n", " def __init__(self, device=None):\n", " self.device = device or (\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", " self.radgraph = RadGraph(model_type=\"radgraph-xl\", device=self.device)\n", " @staticmethod\n", " def _entity_set(graph):\n", " entities = set()\n", " for e in graph.get(\"entities\", {}).values():\n", " text = \" \".join(e.get(\"tokens\", [])).lower().strip()\n", " if text:\n", " entities.add(text)\n", " return entities\n", " @staticmethod\n", " def _relation_set(graph):\n", " entities = graph.get(\"entities\", {})\n", " triplets = set()\n", " for r in graph.get(\"relations\", []):\n", " head = \" \".join(entities[r[\"head\"]][\"tokens\"]).lower().strip()\n", " tail = \" \".join(entities[r[\"tail\"]][\"tokens\"]).lower().strip()\n", " triplets.add((head, r[\"type\"], tail))\n", " return triplets\n", " @staticmethod\n", " def _f1(tp, fp, fn):\n", " p = tp / (tp + fp + 1e-8)\n", " r = tp / (tp + fn + 1e-8)\n", " f1 = 2*p*r / (p+r+1e-8)\n", " return p,r,f1\n", " def score(self, references, hypotheses):\n", " ref_out = self.radgraph(references)\n", " hyp_out = self.radgraph(hypotheses)\n", " ent_tp=ent_fp=ent_fn=0\n", " rel_tp=rel_fp=rel_fn=0\n", " for k in ref_out.keys():\n", " ref_g = ref_out[k]\n", " hyp_g = hyp_out[k]\n", " ref_e = self._entity_set(ref_g)\n", " hyp_e = self._entity_set(hyp_g)\n", " ent_tp += len(ref_e & hyp_e)\n", " ent_fp += len(hyp_e - ref_e)\n", " ent_fn += len(ref_e - hyp_e)\n", " ref_r = self._relation_set(ref_g)\n", " hyp_r = self._relation_set(hyp_g)\n", " rel_tp += len(ref_r & hyp_r)\n", " rel_fp += len(hyp_r - ref_r)\n", " rel_fn += len(ref_r - hyp_r)\n", " _,_,ent_f1 = self._f1(ent_tp, ent_fp, ent_fn)\n", " _,_,rel_f1 = self._f1(rel_tp, rel_fp, rel_fn)\n", " return {\"Entity_F1\": ent_f1, \"Relation_F1\": rel_f1}\n", "\n", "# -----------------------------\n", "# Evaluate a subset (class or overall)\n", "# -----------------------------\n", "def evaluate_subset(df_subset, device):\n", " refs = df_subset[\"ground_truth_report\"].astype(str).tolist()\n", " hyps = df_subset[\"predicted_report\"].astype(str).tolist()\n", " # detection\n", " ious = [compute_iou(parse_bbox(gt), parse_bbox(pred)) for gt,pred in zip(df_subset[\"gt_bbox\"], df_subset[\"predicted_bbox\"])]\n", " det_metrics = {\n", " \"Mean_IoU\": sum(ious)/max(len(ious),1),\n", " \"mAP@0.5\": sum(i>=0.5 for i in ious)/max(len(ious),1),\n", " \"mAP@0.75\": sum(i>=0.75 for i in ious)/max(len(ious),1)\n", " }\n", " # radgraph\n", " rad_scores = RadGraphF1(device=device).score(refs, hyps)\n", " # chexbert\n", " chex_metric = F1CheXbert(device=device)\n", " chex_scores = [chex_metric(refs=[r], hyps=[h]) for r,h in zip(refs, hyps)]\n", " chex_df = pd.DataFrame(chex_scores)\n", " chex_mean = chex_df.mean(numeric_only=True).to_dict()\n", " # nlp metrics\n", " rouge_scorer_obj = rouge_scorer.RougeScorer(['rouge1','rouge2','rougeL'], use_stemmer=True)\n", " smoothie = SmoothingFunction().method4\n", " rouge1,rouge2,rougel,bleu,meteor=[],[],[],[],[]\n", " valid_gt, valid_pred=[],[]\n", " for r,h in zip(refs,hyps):\n", " scores = rouge_scorer_obj.score(r,h)\n", " rouge1.append(scores['rouge1'].fmeasure)\n", " rouge2.append(scores['rouge2'].fmeasure)\n", " rougel.append(scores['rougeL'].fmeasure)\n", " ref_tokens = nltk.word_tokenize(r.lower())\n", " hyp_tokens = nltk.word_tokenize(h.lower())\n", " bleu.append(sentence_bleu([ref_tokens], hyp_tokens, smoothing_function=smoothie))\n", " meteor.append(meteor_score([ref_tokens], hyp_tokens))\n", " valid_gt.append(r)\n", " valid_pred.append(h)\n", " _,_,bert_f1 = bert_score(valid_pred, valid_gt, model_type=\"microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext\", num_layers=9, device=device, rescale_with_baseline=False)\n", " nlp_metrics = {\n", " \"ROUGE1\": sum(rouge1)/max(len(rouge1),1),\n", " \"ROUGE2\": sum(rouge2)/max(len(rouge2),1),\n", " \"ROUGEL\": sum(rougel)/max(len(rougel),1),\n", " \"BLEU\": sum(bleu)/max(len(bleu),1),\n", " \"METEOR\": sum(meteor)/max(len(meteor),1),\n", " \"BERTScore_F1\": bert_f1.mean().item()\n", " }\n", " # cider\n", " cider_metric = CIDErMetric()\n", " cider_score = cider_metric.score(refs, hyps)\n", " # combine\n", " final = {}\n", " final.update(det_metrics)\n", " final.update(rad_scores)\n", " final.update(nlp_metrics)\n", " final[\"CIDEr\"] = cider_score[\"CIDEr\"]\n", " final.update({f\"CheX_{k}\":v for k,v in chex_mean.items()})\n", " return final\n", "\n", "# -----------------------------\n", "# Main\n", "# -----------------------------\n", "def main():\n", " csv_path = \"/home/shanin/Desktop/SHANIN/EyeGaze/CHEST/MODEL/93_ALL/final_combined_results.csv\"\n", " df = pd.read_csv(csv_path)\n", " df = df.dropna(subset=[\"ground_truth_report\",\"predicted_report\",\"ground_truth_disease\",\"predicted_disease\",\"gt_bbox\",\"predicted_bbox\"])\n", " device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", " print(f\"\\nUsing device: {device}\")\n", " # overall\n", " print(\"Computing OVERALL metrics...\")\n", " overall = evaluate_subset(df, device)\n", " overall[\"Class\"] = \"ALL\"\n", " overall[\"Samples\"] = len(df)\n", " # class-wise\n", " rows = [overall]\n", " classes = sorted(df[\"ground_truth_disease\"].unique())\n", " for cls in classes:\n", " df_cls = df[df[\"ground_truth_disease\"]==cls]\n", " metrics = evaluate_subset(df_cls, device)\n", " metrics[\"Class\"] = cls\n", " metrics[\"Samples\"] = len(df_cls)\n", " rows.append(metrics)\n", " final_df = pd.DataFrame(rows)\n", " # display\n", " display_cols = [\"Class\",\"Samples\",\"Mean_IoU\",\"mAP@0.5\",\"mAP@0.75\",\"Entity_F1\",\"Relation_F1\",\"ROUGE1\",\"ROUGE2\",\"ROUGEL\",\"BLEU\",\"METEOR\",\"CIDEr\",\"BERTScore_F1\"]\n", " chex_cols = [c for c in final_df.columns if c.startswith(\"CheX_\")]\n", " display_cols.extend(sorted(chex_cols))\n", " print(\"\\n================ FINAL METRICS TABLE ================\")\n", " print(tabulate(final_df[display_cols].round(4), headers=\"keys\", tablefmt=\"pretty\", showindex=False))\n", "\n", "if __name__ == \"__main__\":\n", " main()\n" ] } ], "metadata": { "accelerator": "GPU", "colab": { "gpuType": "T4", "provenance": [] }, "kernelspec": { "display_name": "llm", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.11" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "01a4aefee71f4f68875c2e3572db50ef": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "02cf2676f874456f9a5b83012008d9ba": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "0403ae9fe7004e34a06cbce76d42b641": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "04eed28ede0544b3acd1709129e63ea4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "05c53e525b1346f68c6434ab781b7629": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2823d0fd91844f1daf7a5f51c6c9a972", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_f7946476f3904b06be92936f54dedae8", "value": 1 } }, "07e379cb99154b728443c08f821303c5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "0b489d8cabe84ea8822fbbe69ddea6ec": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0cde70fedae0455fad85a009b0f05eae": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "0d9f25e7ccc34bf8a1a393ffecdd2423": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d76f682126cd47fea6e45a3e2879a20d", "max": 350, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_544aa96debc740929b82bb98f5c048f0", "value": 350 } }, "0e20fb6770524e0c8f8327ea89158da2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_5ea362f87e9a49d1a4595135ed737131", "IPY_MODEL_e7b80bc1e692486187e85f2af7bbf766", "IPY_MODEL_b41b615e3db04d95a375c8675ac98f5e" ], "layout": "IPY_MODEL_e09c9da093834cd588c582dbe3d834b3" } }, "0e227bfaa33c46df980d47744e5ac3e6": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0f27fa287db245558b8b5a472724a4dc": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1237c5d0d49347ce8ff1ea88febfc00b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_513889de43264bf4a8d2743c9c678bf8", "IPY_MODEL_6bcfe831f391453c9a0cb7a524ad64c0", "IPY_MODEL_2064375e3eb640978ed0204e06c63daf" ], "layout": "IPY_MODEL_4e990d4554ac495ba4831bf1e83c2eaf" } }, "154db1f768174f998292d6fd79fa2636": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "16b406993f82408ab1b1a4725af91fc5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_5744b578842944828708926de5d5c697", "IPY_MODEL_38e15870dabc42bebcb1d0721463765f", "IPY_MODEL_19f779edce12407d9abcd7f56874c267" ], "layout": "IPY_MODEL_c69684207d6d4198933586a0b97b8d3c" } }, "17403e85452c4c1fb7166185857e0883": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_5e7a5e1f12c64d878133502901e5bd3c", "IPY_MODEL_d2ff54ec49174c51b34170a09ab9d710", "IPY_MODEL_5c36b42f495e46e2a3327b6c48580e37" ], "layout": "IPY_MODEL_5d332903ab6d45a0a9255ac320d6ddb1" } }, "1756b6feb6624333a19808052f507e3e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "18e00890879b4d85a77166fcb19518b8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "19f779edce12407d9abcd7f56874c267": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ac1faa8db0774e9f9bf25e422fca1fc5", "placeholder": "​", "style": "IPY_MODEL_32850e5661db4e7a8db80f7c9e3797dd", "value": " 1.05k/? [00:00<00:00, 111kB/s]" } }, "1d5fb1740e544f239878bc3abf3595bd": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1d7359e227b34c4bab4cbdbc96e8f31c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d22190567cfb4fb09f06e30465ee4ecd", "placeholder": "​", "style": "IPY_MODEL_18e00890879b4d85a77166fcb19518b8", "value": " 2.78M/? [00:00<00:00, 57.5MB/s]" } }, "2064375e3eb640978ed0204e06c63daf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_84fce999df6f4101904c5a46c0e4dfb4", "placeholder": "​", "style": "IPY_MODEL_b364c8a6ebd6406bb183b0a764a1a523", "value": " 1.67M/? [00:00<00:00, 50.2MB/s]" } }, "21ea92e08f104ddd8fccffe66d67eae1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "2234569c0aec4ed7a97fe9348b1c5f33": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "22633b763909428f82953a07a87d78b8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_52b0deb295e94dda85d73594744d523b", "placeholder": "​", "style": "IPY_MODEL_3e10bfba6a644484a64f4c033d8715c2", "value": "tokenizer.json: 100%" } }, "232a527afd0b443ca962416ee954cd6f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "25269e443c904728bffd7c7fe1ceb1f6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "257a0377f2304eb58cc6c63a587acd8d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b90a575197d84be191f960f1ab119b8d", "placeholder": "​", "style": "IPY_MODEL_1756b6feb6624333a19808052f507e3e", "value": "tokenizer.json: " } }, "2580b4e469ea44149026417447c0bf77": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "25ae9804eb0c4cc2b3f4c5c4220cf89d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e00cfe826fd04b1f866e9aadc98d8c93", "placeholder": "​", "style": "IPY_MODEL_d28b9fc961494d9b9be6486355d9ece7", "value": " 614/614 [00:00<00:00, 87.2kB/s]" } }, "270d337be1104b15be947dacb3d1fca4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "277b7fcf492f461b922767b425ddfd51": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "2823d0fd91844f1daf7a5f51c6c9a972": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "28b2a527e8004669bfb48bb2ee9f206a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_fcc2195ce5d84f7080f8c3d47d1d2816", "IPY_MODEL_bff98fe2e86d4ab0b66fa083ae74ce41", "IPY_MODEL_a0a5de0898a64bf49bacb2db2c4b252e" ], "layout": "IPY_MODEL_ce9a10d228724a3a9d70329b8fd7c47c" } }, "2a445e689b9345a38b672ac22b76a855": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "2d90c6ceff7d4e91a5313d4d8dcc2e31": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "2f873b479d88453b95cb013de7f766be": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b06c56d1a2284119b7f8005db1ba984f", "placeholder": "​", "style": "IPY_MODEL_232a527afd0b443ca962416ee954cd6f", "value": " 1.67M/? [00:00<00:00, 54.0MB/s]" } }, "31118ef02e08414aa66cb5ff6e6c7514": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "322a4ac26c024fe287f6215738b5b2da": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0403ae9fe7004e34a06cbce76d42b641", "placeholder": "​", "style": "IPY_MODEL_154db1f768174f998292d6fd79fa2636", "value": "chat_template.jinja: " } }, "32850e5661db4e7a8db80f7c9e3797dd": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "329ac9f854cb451f99a63332c7273350": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "32d84fff85134a1db868626f42d5f33c": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "337c412fa8ae4749a380f2eeb1ac241f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "34ed2cddfbb74516ad9f75652424cde2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "38d10bd1f94f4ecb985fcef0b9c521d3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "38e15870dabc42bebcb1d0721463765f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2a445e689b9345a38b672ac22b76a855", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_96f078b15a5648fe8030ed4920aefbbc", "value": 1 } }, "3b24d1d17ad4449daec5abd4cffeabab": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "3b4d094f37284fa2bc736a67b817e454": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "3beb98c5640045a097f12b0cc50cdd36": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "3defc7194f144bdca601b0b959f606f1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3e10bfba6a644484a64f4c033d8715c2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "3e6eee01b06742c1a8485617625fe137": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3fd4646511914c6c85c6def63397c803": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f6add67852044c4fb0f51673be16b893", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_b3287fb39e9a4ae2b6a9a9d542c4294d", "value": 1 } }, "4284d348209d4ce3a6f7ad0ce6d411a3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "43e2323030e34f46856104d3912a7357": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "471b153d9074476085266dc63a9e8453": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "48233afee324459fa8d4dfcf332623c9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4890ed78674f4b03a5f6e4356dc7311f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8d4bc08f060c4139a07c76b2e1c33fb2", "placeholder": "​", "style": "IPY_MODEL_6d6ecd7462464623b1e218678a19e379", "value": "added_tokens.json: 100%" } }, "48f8f7cda86944f39476ba97dc376bd1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4d9943cb14b7450e97b41dc2f3f76709": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "4e0551b2d62c478e99c9483137e5e7ba": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_48f8f7cda86944f39476ba97dc376bd1", "max": 11421896, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_07e379cb99154b728443c08f821303c5", "value": 11421896 } }, "4e990d4554ac495ba4831bf1e83c2eaf": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4f1bcfb138cc4987ad43f6144378344b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "4f57d6f9e21f4699becdbdb8e5c2cf01": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "506c02e216be4252923ebf4bff9bfb3f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "513889de43264bf4a8d2743c9c678bf8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_01a4aefee71f4f68875c2e3572db50ef", "placeholder": "​", "style": "IPY_MODEL_bcdab2d95a204ee999cecc1f24afad1b", "value": "merges.txt: " } }, "52b0deb295e94dda85d73594744d523b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "541d7d11e9bb43b1a4e1dc2d0454e25a": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "544aa96debc740929b82bb98f5c048f0": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "55d9488bfef24ec0bb696261664db48b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_88c32ffba0af4b61b7ccb315705d71fd", "IPY_MODEL_0d9f25e7ccc34bf8a1a393ffecdd2423", "IPY_MODEL_97c86a2d7d9d44b7a4d663c68b806054" ], "layout": "IPY_MODEL_6dd95157f0874d59ba124934ea324e7d" } }, "563f9674405b46348511cd4f401f9523": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "56b79f86e7b44c84bab417cb2e543270": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f7c6b573ba814329ad14e728627683e8", "max": 935, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_3beb98c5640045a097f12b0cc50cdd36", "value": 935 } }, "56d3f120efba43ab9d6691906d07a2f1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_cff6d60f51374e0e9dec98ff9a3bea08", "IPY_MODEL_fd31b26fba6e403b8d3167c077eade6c", "IPY_MODEL_99d71706a23b4241a5b7e073e745f791" ], "layout": "IPY_MODEL_506c02e216be4252923ebf4bff9bfb3f" } }, "5744b578842944828708926de5d5c697": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_48233afee324459fa8d4dfcf332623c9", "placeholder": "​", "style": "IPY_MODEL_471b153d9074476085266dc63a9e8453", "value": "chat_template.json: " } }, "576ba493cfe84f7dab73d166c2609c7b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "57ff204a78df4d39a33c7a7f0822bb55": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_6ec4cf9385b74541abbb639bddcf04d8", "IPY_MODEL_5a7cb1594b264fe38f35f2dacc7fb480", "IPY_MODEL_740aadf9626d4521a213c531ef95a8e3" ], "layout": "IPY_MODEL_ec4bd2e7a974404f98fcaf23971e23fc" } }, "5a682e13d4c64e61a980b01c61d27239": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5a7cb1594b264fe38f35f2dacc7fb480": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_32d84fff85134a1db868626f42d5f33c", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_9f0ea766f5e746c083e7af4d7c4a65dc", "value": 1 } }, "5c36b42f495e46e2a3327b6c48580e37": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_337c412fa8ae4749a380f2eeb1ac241f", "placeholder": "​", "style": "IPY_MODEL_04eed28ede0544b3acd1709129e63ea4", "value": " 791/791 [00:00<00:00, 20.1kB/s]" } }, "5c4cf45e5bcd4f3ab86dd5ee6014702f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_615592a5e55e43b7b5c4b6003df3f4a4", "IPY_MODEL_ce819f97526148dd868d7865e0050250", "IPY_MODEL_bf91e8d2b3d54934a1b792847d1b60d7" ], "layout": "IPY_MODEL_0f27fa287db245558b8b5a472724a4dc" } }, "5d332903ab6d45a0a9255ac320d6ddb1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5e7a5e1f12c64d878133502901e5bd3c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ae73faebc89b4c24888893921aedc29c", "placeholder": "​", "style": "IPY_MODEL_70286b77c3554df9b01946c85356b940", "value": "preprocessor_config.json: 100%" } }, "5ea362f87e9a49d1a4595135ed737131": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_df18300b8fe543faa3905032c24d7265", "placeholder": "​", "style": "IPY_MODEL_f3ec43a01b5a4d258d3d27a8196af437", "value": "vocab.json: " } }, "5f6b06d2611c40c59ab259f9b37d7fc7": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "60e3c762040e45bd91e35b5626571f74": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "615592a5e55e43b7b5c4b6003df3f4a4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b37183a361974bc4952ccdd8b5feba77", "placeholder": "​", "style": "IPY_MODEL_ff90238949574f7b99fbf78d03502a4b", "value": "model.safetensors: 100%" } }, "6562de7b97b345908bf36ef141e3521b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_92e8daf371734130b095b7facd5c34fa", "placeholder": "​", "style": "IPY_MODEL_c141805d36ce4dd4bad0fff565c30e74", "value": "tokenizer_config.json: " } }, "66d3b102e0de4be0ad56cfdf514078db": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "697bf69e98aa49969c2074f7ab229a4f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "6a7d6ab9863c48c099454bb73d53b61e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_322a4ac26c024fe287f6215738b5b2da", "IPY_MODEL_05c53e525b1346f68c6434ab781b7629", "IPY_MODEL_79434a3e6e70481ba1cbafccc5285ecb" ], "layout": "IPY_MODEL_0e227bfaa33c46df980d47744e5ac3e6" } }, "6bcfe831f391453c9a0cb7a524ad64c0": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_02cf2676f874456f9a5b83012008d9ba", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_70563f0b08e54f13a0d57b8541779018", "value": 1 } }, "6c1d055b32b642198c97be66b927d446": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "6c22c9a2bbbc4dd4aef35334ba02bda3": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6d6ecd7462464623b1e218678a19e379": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6d78ad3adac749e69c928b3a90567ba6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6dd95157f0874d59ba124934ea324e7d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6ec4cf9385b74541abbb639bddcf04d8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a2e92ed58d994ebc871b605206fbf49f", "placeholder": "​", "style": "IPY_MODEL_ccdd3a92abc746c2a845e3aa5e0718a5", "value": "tokenizer_config.json: " } }, "70286b77c3554df9b01946c85356b940": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "70563f0b08e54f13a0d57b8541779018": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "7109de9f466c4f32a925b76034584226": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "7134af62dd5044ab8335531c83330219": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "72d501ddf0f94e6bb274f6956af2be07": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e9c47a8513814bf0be84ba7897dfd261", "max": 614, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_96b042bd9efe4120ab2fd378fd4a36e7", "value": 614 } }, "73c071d37f384a698fd32b7de32762f9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "740aadf9626d4521a213c531ef95a8e3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_541d7d11e9bb43b1a4e1dc2d0454e25a", "placeholder": "​", "style": "IPY_MODEL_34ed2cddfbb74516ad9f75652424cde2", "value": " 5.80k/? [00:00<00:00, 318kB/s]" } }, "75c7c7a6c6b74632a67c29d7365a6a04": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_ba4dd1ddfd874a9a8f99336e6ab61b3e", "IPY_MODEL_f3f4a0470a4a4f95af5037b96575dbe7", "IPY_MODEL_1d7359e227b34c4bab4cbdbc96e8f31c" ], "layout": "IPY_MODEL_21ea92e08f104ddd8fccffe66d67eae1" } }, "766cb257f49c4125aa0ced85df2e7f8c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_22633b763909428f82953a07a87d78b8", "IPY_MODEL_4e0551b2d62c478e99c9483137e5e7ba", "IPY_MODEL_ea3c74099bca426989afa332b2e660d3" ], "layout": "IPY_MODEL_277b7fcf492f461b922767b425ddfd51" } }, "79434a3e6e70481ba1cbafccc5285ecb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d86f568779fc4e53a6310d087393ccf2", "placeholder": "​", "style": "IPY_MODEL_4d9943cb14b7450e97b41dc2f3f76709", "value": " 1.02k/? [00:00<00:00, 108kB/s]" } }, "7c70f5fd11954f49a25bfb5ebd2e29b0": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "84fce999df6f4101904c5a46c0e4dfb4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "852e1eafe30944589d8353cc0774401b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_8c66db9882fa43feb3564275a0a144bb", "IPY_MODEL_56b79f86e7b44c84bab417cb2e543270", "IPY_MODEL_bcb73fefa76840f9a69a172fd7e78dd7" ], "layout": "IPY_MODEL_c2d3603dab544ceeb0a8880526264396" } }, "88c32ffba0af4b61b7ccb315705d71fd": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_31118ef02e08414aa66cb5ff6e6c7514", "placeholder": "​", "style": "IPY_MODEL_0cde70fedae0455fad85a009b0f05eae", "value": "preprocessor_config.json: 100%" } }, "8c66db9882fa43feb3564275a0a144bb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_563f9674405b46348511cd4f401f9523", "placeholder": "​", "style": "IPY_MODEL_66d3b102e0de4be0ad56cfdf514078db", "value": "video_preprocessor_config.json: 100%" } }, "8d4bc08f060c4139a07c76b2e1c33fb2": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "92e8daf371734130b095b7facd5c34fa": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "95852c7235524df6baae36d4937e67ed": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_7c70f5fd11954f49a25bfb5ebd2e29b0", "max": 605, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_7134af62dd5044ab8335531c83330219", "value": 605 } }, "96b042bd9efe4120ab2fd378fd4a36e7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "96f078b15a5648fe8030ed4920aefbbc": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "97c86a2d7d9d44b7a4d663c68b806054": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a3006a8cb1fc4c519e57c29d798b9768", "placeholder": "​", "style": "IPY_MODEL_2d90c6ceff7d4e91a5313d4d8dcc2e31", "value": " 350/350 [00:00<00:00, 23.4kB/s]" } }, "980261fb60494e499b6c012c359576e1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_4890ed78674f4b03a5f6e4356dc7311f", "IPY_MODEL_95852c7235524df6baae36d4937e67ed", "IPY_MODEL_e47a8fc89049437182f2f453c15b105d" ], "layout": "IPY_MODEL_3e6eee01b06742c1a8485617625fe137" } }, "98094a2c7de84ff8b29dd56e88f646ae": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "99d71706a23b4241a5b7e073e745f791": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2234569c0aec4ed7a97fe9348b1c5f33", "placeholder": "​", "style": "IPY_MODEL_d6e72b9158874e64ad54bb00262d505d", "value": " 237/237 [00:00<00:00, 24.6kB/s]" } }, "9b925356804d467ea3d802f804067ad5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "9f0ea766f5e746c083e7af4d7c4a65dc": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "9f45ebf9037141148bed50d5e0647c64": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c26640d94f3c46439750f9ee3bf8efde", "placeholder": "​", "style": "IPY_MODEL_ea7ad5028b374f0ab5616881432292e3", "value": " 7.03M/? [00:00<00:00, 72.8MB/s]" } }, "9f707b2340454a81b381eea740ace9a3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6c1d055b32b642198c97be66b927d446", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_dc6dfa275de142db96a9c2b96c0b2f38", "value": 1 } }, "a0a5de0898a64bf49bacb2db2c4b252e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_fe48027a0bc94da7a9f200f2503bf48e", "placeholder": "​", "style": "IPY_MODEL_afb2a13643ed451db7d880421d1e1bf7", "value": " 1.05k/? [00:00<00:00, 64.8kB/s]" } }, "a0f325a33cef4b7fb4fe1bf0352a44c3": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a2e92ed58d994ebc871b605206fbf49f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a3006a8cb1fc4c519e57c29d798b9768": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a7a56cd6c6234343a4da9a448acd94c7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "ac1faa8db0774e9f9bf25e422fca1fc5": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ae73faebc89b4c24888893921aedc29c": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "afb2a13643ed451db7d880421d1e1bf7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "b06c56d1a2284119b7f8005db1ba984f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "b0707545040c439f9da77d20abae7439": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_bcd8dac75a1f45dfa8e40c09e0c4aabb", "IPY_MODEL_3fd4646511914c6c85c6def63397c803", "IPY_MODEL_2f873b479d88453b95cb013de7f766be" ], "layout": "IPY_MODEL_60e3c762040e45bd91e35b5626571f74" } }, "b3287fb39e9a4ae2b6a9a9d542c4294d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "b364c8a6ebd6406bb183b0a764a1a523": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "b37183a361974bc4952ccdd8b5feba77": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "b41b615e3db04d95a375c8675ac98f5e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_fbaf2d5e764c4cfdaeeb1ad0594c1bb4", "placeholder": "​", "style": "IPY_MODEL_e06ef7766d644508acc14baf4cfb2272", "value": " 2.78M/? [00:00<00:00, 35.9MB/s]" } }, "b6b11430259347a58075d298f397903a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_270d337be1104b15be947dacb3d1fca4", "placeholder": "​", "style": "IPY_MODEL_6d78ad3adac749e69c928b3a90567ba6", "value": "special_tokens_map.json: 100%" } }, "b90a575197d84be191f960f1ab119b8d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ba4dd1ddfd874a9a8f99336e6ab61b3e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_5a682e13d4c64e61a980b01c61d27239", "placeholder": "​", "style": "IPY_MODEL_7109de9f466c4f32a925b76034584226", "value": "vocab.json: " } }, "bb7363e8e32142548f419f8a67d529e8": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "bcb73fefa76840f9a69a172fd7e78dd7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e6b6705e66934a03acd5c5fed825b2ff", "placeholder": "​", "style": "IPY_MODEL_be84a30bc3aa4421897171ba4d321076", "value": " 935/935 [00:00<00:00, 104kB/s]" } }, "bcd8dac75a1f45dfa8e40c09e0c4aabb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a0f325a33cef4b7fb4fe1bf0352a44c3", "placeholder": "​", "style": "IPY_MODEL_f98630edbd6c4f08b33958e9322abc40", "value": "merges.txt: " } }, "bcdab2d95a204ee999cecc1f24afad1b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "be84a30bc3aa4421897171ba4d321076": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "bf91e8d2b3d54934a1b792847d1b60d7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f3ae9638777040f4b464a3ff4e20350f", "placeholder": "​", "style": "IPY_MODEL_4f1bcfb138cc4987ad43f6144378344b", "value": " 6.90G/6.90G [01:20<00:00, 57.6MB/s]" } }, "bff98fe2e86d4ab0b66fa083ae74ce41": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_5f6b06d2611c40c59ab259f9b37d7fc7", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_cf3ee86ef8e14f2d8b3991c61789f4e0", "value": 1 } }, "c141805d36ce4dd4bad0fff565c30e74": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "c26640d94f3c46439750f9ee3bf8efde": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c2d3603dab544ceeb0a8880526264396": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c360b40ba1ba44b498b63c21b43635e0": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_697bf69e98aa49969c2074f7ab229a4f", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_ed671b2d259c4acd96868ba7012c30bf", "value": 1 } }, "c45d64c50342423fb7df622d7e37e7e6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "c69684207d6d4198933586a0b97b8d3c": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c950477fe178495ea399f5ad35b9c8aa": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_6562de7b97b345908bf36ef141e3521b", "IPY_MODEL_c360b40ba1ba44b498b63c21b43635e0", "IPY_MODEL_f33d596931ca4662a90b2199bbca9ba4" ], "layout": "IPY_MODEL_1d5fb1740e544f239878bc3abf3595bd" } }, "ccdd3a92abc746c2a845e3aa5e0718a5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "ce819f97526148dd868d7865e0050250": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0b489d8cabe84ea8822fbbe69ddea6ec", "max": 6900397310, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_43e2323030e34f46856104d3912a7357", "value": 6900397310 } }, "ce9a10d228724a3a9d70329b8fd7c47c": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "cf3ee86ef8e14f2d8b3991c61789f4e0": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "cff6d60f51374e0e9dec98ff9a3bea08": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_73c071d37f384a698fd32b7de32762f9", "placeholder": "​", "style": "IPY_MODEL_3b4d094f37284fa2bc736a67b817e454", "value": "generation_config.json: 100%" } }, "d0a5cc16a8f64458979923e8664ebcf5": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d22190567cfb4fb09f06e30465ee4ecd": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d28b9fc961494d9b9be6486355d9ece7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "d2ff54ec49174c51b34170a09ab9d710": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d0a5cc16a8f64458979923e8664ebcf5", "max": 791, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_25269e443c904728bffd7c7fe1ceb1f6", "value": 791 } }, "d6e72b9158874e64ad54bb00262d505d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "d76f682126cd47fea6e45a3e2879a20d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d86f568779fc4e53a6310d087393ccf2": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "dc6dfa275de142db96a9c2b96c0b2f38": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "df18300b8fe543faa3905032c24d7265": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e00cfe826fd04b1f866e9aadc98d8c93": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e06ef7766d644508acc14baf4cfb2272": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e09c9da093834cd588c582dbe3d834b3": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e141541d78ff422687947fc5cacb2bea": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_b6b11430259347a58075d298f397903a", "IPY_MODEL_72d501ddf0f94e6bb274f6956af2be07", "IPY_MODEL_25ae9804eb0c4cc2b3f4c5c4220cf89d" ], "layout": "IPY_MODEL_329ac9f854cb451f99a63332c7273350" } }, "e47a8fc89049437182f2f453c15b105d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_bb7363e8e32142548f419f8a67d529e8", "placeholder": "​", "style": "IPY_MODEL_9b925356804d467ea3d802f804067ad5", "value": " 605/605 [00:00<00:00, 33.2kB/s]" } }, "e6b6705e66934a03acd5c5fed825b2ff": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e7b80bc1e692486187e85f2af7bbf766": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_98094a2c7de84ff8b29dd56e88f646ae", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_4f57d6f9e21f4699becdbdb8e5c2cf01", "value": 1 } }, "e9c47a8513814bf0be84ba7897dfd261": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ea3c74099bca426989afa332b2e660d3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6c22c9a2bbbc4dd4aef35334ba02bda3", "placeholder": "​", "style": "IPY_MODEL_c45d64c50342423fb7df622d7e37e7e6", "value": " 11.4M/11.4M [00:00<00:00, 21.4MB/s]" } }, "ea7ad5028b374f0ab5616881432292e3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "ec4bd2e7a974404f98fcaf23971e23fc": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ed671b2d259c4acd96868ba7012c30bf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "ee70e3f3d12d49ff8b3f8e210e27a00b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f2185a9d66e64032bce14f1fb1315925": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_257a0377f2304eb58cc6c63a587acd8d", "IPY_MODEL_9f707b2340454a81b381eea740ace9a3", "IPY_MODEL_9f45ebf9037141148bed50d5e0647c64" ], "layout": "IPY_MODEL_ee70e3f3d12d49ff8b3f8e210e27a00b" } }, "f33d596931ca4662a90b2199bbca9ba4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_3defc7194f144bdca601b0b959f606f1", "placeholder": "​", "style": "IPY_MODEL_38d10bd1f94f4ecb985fcef0b9c521d3", "value": " 5.70k/? [00:00<00:00, 202kB/s]" } }, "f3ae9638777040f4b464a3ff4e20350f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f3dfbed832474773ae7b0daa520c7782": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "f3ec43a01b5a4d258d3d27a8196af437": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "f3f4a0470a4a4f95af5037b96575dbe7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f3dfbed832474773ae7b0daa520c7782", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_3b24d1d17ad4449daec5abd4cffeabab", "value": 1 } }, "f6add67852044c4fb0f51673be16b893": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "20px" } }, "f7946476f3904b06be92936f54dedae8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "f7c6b573ba814329ad14e728627683e8": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f98630edbd6c4f08b33958e9322abc40": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "fbaf2d5e764c4cfdaeeb1ad0594c1bb4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "fcc2195ce5d84f7080f8c3d47d1d2816": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_576ba493cfe84f7dab73d166c2609c7b", "placeholder": "​", "style": "IPY_MODEL_a7a56cd6c6234343a4da9a448acd94c7", "value": "chat_template.json: " } }, "fd31b26fba6e403b8d3167c077eade6c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2580b4e469ea44149026417447c0bf77", "max": 237, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_4284d348209d4ce3a6f7ad0ce6d411a3", "value": 237 } }, "fe48027a0bc94da7a9f200f2503bf48e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ff90238949574f7b99fbf78d03502a4b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } } } } }, "nbformat": 4, "nbformat_minor": 0 }