Upload 9 files

Running_code.ipynb

@@ -0,0 +1,204 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\Srujan Jujare\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer\n",
+    "import torch\n",
+    "from PIL import Image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "VisionEncoderDecoderModel(\n",
+       "  (encoder): ViTModel(\n",
+       "    (embeddings): ViTEmbeddings(\n",
+       "      (patch_embeddings): ViTPatchEmbeddings(\n",
+       "        (projection): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16))\n",
+       "      )\n",
+       "      (dropout): Dropout(p=0.0, inplace=False)\n",
+       "    )\n",
+       "    (encoder): ViTEncoder(\n",
+       "      (layer): ModuleList(\n",
+       "        (0-11): 12 x ViTLayer(\n",
+       "          (attention): ViTAttention(\n",
+       "            (attention): ViTSelfAttention(\n",
+       "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
+       "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
+       "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
+       "              (dropout): Dropout(p=0.0, inplace=False)\n",
+       "            )\n",
+       "            (output): ViTSelfOutput(\n",
+       "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "              (dropout): Dropout(p=0.0, inplace=False)\n",
+       "            )\n",
+       "          )\n",
+       "          (intermediate): ViTIntermediate(\n",
+       "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "            (intermediate_act_fn): GELUActivation()\n",
+       "          )\n",
+       "          (output): ViTOutput(\n",
+       "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "            (dropout): Dropout(p=0.0, inplace=False)\n",
+       "          )\n",
+       "          (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "        )\n",
+       "      )\n",
+       "    )\n",
+       "    (layernorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "    (pooler): ViTPooler(\n",
+       "      (dense): Linear(in_features=768, out_features=768, bias=True)\n",
+       "      (activation): Tanh()\n",
+       "    )\n",
+       "  )\n",
+       "  (decoder): GPT2LMHeadModel(\n",
+       "    (transformer): GPT2Model(\n",
+       "      (wte): Embedding(50257, 768)\n",
+       "      (wpe): Embedding(1024, 768)\n",
+       "      (drop): Dropout(p=0.1, inplace=False)\n",
+       "      (h): ModuleList(\n",
+       "        (0-11): 12 x GPT2Block(\n",
+       "          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
+       "          (attn): GPT2Attention(\n",
+       "            (c_attn): Conv1D()\n",
+       "            (c_proj): Conv1D()\n",
+       "            (attn_dropout): Dropout(p=0.1, inplace=False)\n",
+       "            (resid_dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
+       "          (crossattention): GPT2Attention(\n",
+       "            (c_attn): Conv1D()\n",
+       "            (q_attn): Conv1D()\n",
+       "            (c_proj): Conv1D()\n",
+       "            (attn_dropout): Dropout(p=0.1, inplace=False)\n",
+       "            (resid_dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "          (ln_cross_attn): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
+       "          (mlp): GPT2MLP(\n",
+       "            (c_fc): Conv1D()\n",
+       "            (c_proj): Conv1D()\n",
+       "            (act): NewGELUActivation()\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "          )\n",
+       "        )\n",
+       "      )\n",
+       "      (ln_f): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
+       "    )\n",
+       "    (lm_head): Linear(in_features=768, out_features=50257, bias=False)\n",
+       "  )\n",
+       ")"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = VisionEncoderDecoderModel.from_pretrained(\"nlpconnect/vit-gpt2-image-captioning\")\n",
+    "feature_extractor = ViTImageProcessor.from_pretrained(\"nlpconnect/vit-gpt2-image-captioning\")\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\"nlpconnect/vit-gpt2-image-captioning\")\n",
+    "\n",
+    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "model.to(device)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "max_length = 16\n",
+    "num_beams = 4\n",
+    "gen_kwargs = {\"max_length\": max_length, \"num_beams\": num_beams}\n",
+    "def predict_step(image_paths):\n",
+    "  images = []\n",
+    "  for image_path in image_paths:\n",
+    "    i_image = Image.open(image_path)\n",
+    "    if i_image.mode != \"RGB\":\n",
+    "      i_image = i_image.convert(mode=\"RGB\")\n",
+    "\n",
+    "    images.append(i_image)\n",
+    "\n",
+    "  pixel_values = feature_extractor(images=images, return_tensors=\"pt\").pixel_values\n",
+    "  pixel_values = pixel_values.to(device)\n",
+    "\n",
+    "  output_ids = model.generate(pixel_values, **gen_kwargs)\n",
+    "\n",
+    "  preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)\n",
+    "  preds = [pred.strip() for pred in preds]\n",
+    "  return preds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "We strongly recommend passing in an `attention_mask` since your input_ids may be padded. See https://huggingface.co/docs/transformers/troubleshooting#incorrect-output-when-padding-tokens-arent-masked.\n",
+      "You may ignore this warning if your `pad_token_id` (50256) is identical to the `bos_token_id` (50256), `eos_token_id` (50256), or the `sep_token_id` (None), and your input is not padded.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "['a clock on a dashboard of a car']"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predict_step(['D:\\\\Validation\\\\Class 2\\\\i17.jpg'])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.11.5"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

config.json

@@ -0,0 +1,177 @@
+{
+  "_name_or_path": "vit-gpt-pt",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_name_or_path": "",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": 50256,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 50256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.15.0",
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.15.0",
+    "use_bfloat16": false
+  },
+  "eos_token_id": 50256,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 50256,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null
+}

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2605a69b760d0b218c3b5d2069ba070d28f279a16ce4bc87bf019b75a91553e6
+size 982141993

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "./models/", "tokenizer_class": "GPT2Tokenizer"}