base

.env

@@ -0,0 +1 @@
+HUGGINGFACE_KEY = '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'

app.py

@@ -0,0 +1,40 @@
+""" Streamlit UI for object detection with DETR. """
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+import streamlit as st
+from PIL import Image
+import pandas as pd
+
+pipe = pipeline("object-detection", model="facebook/detr-resnet-101")
+
+# Set the title
+st.title("Vision Quest 2")
+
+results = None
+image = None
+
+# Create a file uploader and set the upload type to images
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file:
+    upload_image_button = st.button("Upload Image")
+    if upload_image_button:
+        with st.spinner("Uploading Image...")
+            # Convert the image to a file object
+            image = Image.open(uploaded_file)
+            
+            # Process the image through the pipeline
+            results = pipe(image)
+
+col1, col2 = st.columns(2)
+if image and results:
+    with col1:
+        st.image(image, use_column_width=True)
+    with col2:
+        # Display the individual objects, the bounding boxes, and the confidence
+        # And then display the total number of each type of object
+        # Create a dataframe to hold the results
+        df = pd.DataFrame(results)
+        st.dataframe(df)    
+        

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+streamlit
+PIL
+pandas

test.ipynb

@@ -0,0 +1,255 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "27a09705e50844998302f7953225305f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading (…)lve/main/config.json:   0%|          | 0.00/4.38k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b08c2c5730864354b556eee28bf230fe",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading model.safetensors:   0%|          | 0.00/243M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "58774a0b69624064b710db8d601fca0e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading model.safetensors:   0%|          | 0.00/179M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of the model checkpoint at facebook/detr-resnet-101 were not used when initializing DetrForObjectDetection: ['model.backbone.conv_encoder.model.layer1.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer3.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer2.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer4.0.downsample.1.num_batches_tracked']\n",
+      "- This IS expected if you are initializing DetrForObjectDetection from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing DetrForObjectDetection from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b5e6dfa6bff2482faefa2663727a576e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading (…)rocessor_config.json:   0%|          | 0.00/274 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Could not find image processor class in the image processor config or the model config. Loading based on pattern matching with the model's feature extractor configuration.\n",
+      "The `max_size` parameter is deprecated and will be removed in v4.26. Please specify in `size['longest_edge'] instead`.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Use a pipeline as a high-level helper\n",
+    "from transformers import pipeline\n",
+    "\n",
+    "pipe = pipeline(\"object-detection\", model=\"facebook/detr-resnet-101\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'score': 0.9799804091453552,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 601, 'ymin': 366, 'xmax': 638, 'ymax': 429}},\n",
+       " {'score': 0.9278073906898499,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 51, 'ymin': 266, 'xmax': 123, 'ymax': 319}},\n",
+       " {'score': 0.9865541458129883,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 440, 'ymin': 328, 'xmax': 499, 'ymax': 391}},\n",
+       " {'score': 0.9414395093917847,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 291, 'ymin': 337, 'xmax': 373, 'ymax': 402}},\n",
+       " {'score': 0.995155930519104,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 711, 'ymin': 523, 'xmax': 847, 'ymax': 603}},\n",
+       " {'score': 0.9969741106033325,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1042, 'ymin': 588, 'xmax': 1221, 'ymax': 705}},\n",
+       " {'score': 0.9744983911514282,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1474, 'ymin': 408, 'xmax': 1598, 'ymax': 483}},\n",
+       " {'score': 0.9618602991104126,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 584, 'ymin': 684, 'xmax': 779, 'ymax': 810}},\n",
+       " {'score': 0.9941285848617554,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1125, 'ymin': 486, 'xmax': 1249, 'ymax': 579}},\n",
+       " {'score': 0.9376370906829834,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1103, 'ymin': 298, 'xmax': 1172, 'ymax': 341}},\n",
+       " {'score': 0.9970544576644897,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1025, 'ymin': 668, 'xmax': 1211, 'ymax': 805}},\n",
+       " {'score': 0.9351339340209961,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 228, 'ymin': 338, 'xmax': 297, 'ymax': 401}},\n",
+       " {'score': 0.9771629571914673,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1063, 'ymin': 361, 'xmax': 1110, 'ymax': 422}},\n",
+       " {'score': 0.9911984801292419,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 712, 'ymin': 429, 'xmax': 764, 'ymax': 505}},\n",
+       " {'score': 0.9905621409416199,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1073, 'ymin': 446, 'xmax': 1171, 'ymax': 524}},\n",
+       " {'score': 0.9994051456451416,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 594, 'ymin': 593, 'xmax': 1017, 'ymax': 814}},\n",
+       " {'score': 0.9972768425941467,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1399, 'ymin': 593, 'xmax': 1655, 'ymax': 753}},\n",
+       " {'score': 0.993872880935669,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 4, 'ymin': 711, 'xmax': 225, 'ymax': 815}},\n",
+       " {'score': 0.9839267134666443,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 844, 'ymin': 343, 'xmax': 918, 'ymax': 395}},\n",
+       " {'score': 0.977581799030304,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 1179, 'ymin': 367, 'xmax': 1240, 'ymax': 425}},\n",
+       " {'score': 0.9804152250289917,\n",
+       "  'label': 'cow',\n",
+       "  'box': {'xmin': 610, 'ymin': 322, 'xmax': 672, 'ymax': 384}}]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pipe('./cow1.jpg')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results = pipe('./cow1.jpg')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'score': 0.9799804091453552,\n",
+       " 'label': 'cow',\n",
+       " 'box': {'xmin': 601, 'ymin': 366, 'xmax': 638, 'ymax': 429}}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "results[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total cows: 21\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Add together all of the results to get the total number of cows\n",
+    "total_cows = 0\n",
+    "for result in results:\n",
+    "    if result[\"label\"] == \"cow\":\n",
+    "        total_cows += 1\n",
+    "\n",
+    "print(f\"Total cows: {total_cows}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py310",
+   "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": "3.10.12"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}