Upload 2 files

app.py

@@ -0,0 +1,128 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: car_damage_detector.ipynb.
+
+# %% auto 0
+__all__ = ['assets_path', 'models_path', 'examples_path', 'imagenet_labels', 'model', 'transform', 'catogories', 'title',
+           'description', 'examples', 'learn_damaged_or_not', 'learn_damage_location', 'learn_damage_severity', 'intf',
+           'get_imagenet_classes', 'create_model', 'car_or_not_inference', 'predict', 'main_predictor']
+
+# %% car_damage_detector.ipynb 2
+# imports
+# import os
+import timm
+# import json
+import torch
+import gradio as gr
+import pickle as pk
+# from PIL import Image
+import fastbook
+fastbook.setup_book()
+
+from fastbook import *
+from fastai.vision.widgets import * 
+# from collections import Counter, defaultdict
+
+assets_path = 'assets/'
+models_path = 'assets/models/'
+examples_path = 'assets/examples/'
+
+# %% car_damage_detector.ipynb 3
+# Imagenet Class
+def get_imagenet_classes():
+    # read idx file
+    imagenet_file = open(assets_path+"imagenet_class_index.txt", "r").read()
+    # seperate elements and onvert string to list
+    imagenet_labels_raw = imagenet_file.strip().split('\n')
+    # keep first label
+    imagenet_labels = [item.split(',')[0] for item in imagenet_labels_raw]
+    return imagenet_labels
+
+imagenet_labels = get_imagenet_classes()
+
+# Create Model
+def create_model(model_name='vgg16.tv_in1k'):
+    # import required model
+    model = timm.create_model(model_name, pretrained=True).eval()
+    # transform data as required by the model
+    transform = timm.data.create_transform(
+        **timm.data.resolve_data_config(model.pretrained_cfg)
+    )
+    return model, transform
+
+model, transform = create_model()
+
+# Car or Not : Main Inferene Code
+catogories = ('Is a Car', 'Not a Car')
+def car_or_not_inference(input_image):
+
+    # print ("Validating that this is a picture of a car...")
+
+    # retain the top 'n' most occuring items \\ n=36
+    top_n_cat_list  = ['sports_car', 'minivan', 'convertible', 'beach_wagon', 'limousine', 'pickup', 'car_wheel', 'grille', 'racer', 'minibus', 'jeep', 'moving_van', 'tow_truck', 'cab', 'police_van', 'snowplow', 'amphibian', 'trailer_truck', 'recreational_vehicle', 'ambulance', 'motor_scooter', 'cassette_player', 'fire_engine', 'car_mirror', 'mobile_home', 'crash_helmet', 'mouse', 'snowmobile', 'Model_T', 'passenger_car', 'solar_dish', 'garbage_truck', 'photocopier', 'mountain_tent', 'half_track', 'speedboat']
+
+    # image = PILImage.create(input_image)
+    # transform image as required for prediction
+    image_tensor = transform(input_image)
+    # predict on image
+    output = model(image_tensor.unsqueeze(0))
+    # get probabilites
+    probabilities = torch.nn.functional.softmax(output[0], dim=0)
+    # select top 5 probs
+    _, indices = torch.topk(probabilities, 5)
+
+    for idx in indices:
+        pred_label = imagenet_labels[idx]
+        if pred_label in top_n_cat_list:
+            return 1.0 #dict(zip(catogories, [1.0, 0.0])) #"Validation complete - proceed to damage evaluation"
+
+    return 0.0 #dict(zip(catogories, [0.0, 1.0]))#"Are you sure this is a picture of your car? Please take another picture (try a different angle or lighting) and try again."
+
+
+# %% car_damage_detector.ipynb 5
+title = "Car Care"
+description = "A vision based car damage identifier."
+examples = [examples_path+'lambo.jpg', examples_path+'dog.jpg', examples_path+'front_moderate.jpg']
+
+learn_damaged_or_not = load_learner(models_path+'car_damaged_or_not.pkl')
+learn_damage_location = load_learner(models_path+'car_damage_side.pkl')
+learn_damage_severity = load_learner(models_path+'car_damage_severity.pkl')
+
+def predict(img, learn):
+    # img = PILImage.create(img)
+    pred, idx, probs = learn.predict(img)
+    return pred#, float(probs[idx])
+
+def main_predictor(img,  progress=gr.Progress()):
+    
+    progress((0,4), desc="Starting Analysis...")    
+    input_image = PILImage.create(img)
+    car_or_not = car_or_not_inference(input_image)
+
+    progress((1,4))
+    if car_or_not:
+        gr.Info("Car check completed.")
+        damaged_or_not = predict(input_image, learn_damaged_or_not)
+
+        progress((2,4))
+        if damaged_or_not == 'damage':
+            gr.Info("Damage check completed.")
+            damaged_location = predict(input_image, learn_damage_location)
+            progress((3,4))
+            gr.Info("Damage Location identified.")
+            damaged_severity = predict(input_image, learn_damage_severity)
+            progress((4,4), desc="Analysis Complete")
+            gr.Info("Damage Severity assessed.")
+            # refer below sections for Location and Severity
+            return f"""Results: \n Car Check: it's a Car \n Damage Check: Car is Damaged \n Location: {damaged_location} \n Severity: {damaged_severity}"""
+        else:
+            progress((4,4))
+            return "Are you sure your car is damaged ?. \nMake sure you click a clear picture of the damaged portion. \nPlease resubmit the picture"
+    else:
+        progress((4,4))
+        return "Are you sure this is a picture of your car? \nPlease take another picture (try a different angle or lighting) and try again."
+
+# input_image = 'assets/examples/severe.jpg'
+# main_predictor(input_image)
+
+# %% car_damage_detector.ipynb 6
+intf = gr.Interface(fn=main_predictor,inputs=gr.Image(),outputs=gr.Textbox(),title=title,description=description,examples=examples)
+intf.launch(share=True)

car_damage_detector.ipynb

@@ -0,0 +1,304 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1db7d295-3145-4c5d-b140-170265d1d28e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#|default_exp app"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ca158c7d-0ff3-4792-9950-5e7cf8665de2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# changes to do :\n",
+    "# shorten the first runction / damaged or not\n",
+    "# read image in one place\n",
+    "# streamline functions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "24a0e983-2c3a-4150-9113-72ff07e77587",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#|export\n",
+    "# imports\n",
+    "# import os\n",
+    "import timm\n",
+    "# import json\n",
+    "import torch\n",
+    "import gradio as gr\n",
+    "import pickle as pk\n",
+    "# from PIL import Image\n",
+    "import fastbook\n",
+    "fastbook.setup_book()\n",
+    "\n",
+    "from fastbook import *\n",
+    "from fastai.vision.widgets import * \n",
+    "# from collections import Counter, defaultdict\n",
+    "\n",
+    "assets_path = 'assets/'\n",
+    "models_path = 'assets/models/'\n",
+    "examples_path = 'assets/examples/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "43d3ad2d-5d60-4458-8441-1919e6a579f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#|export\n",
+    "# Imagenet Class\n",
+    "def get_imagenet_classes():\n",
+    "    # read idx file\n",
+    "    imagenet_file = open(assets_path+\"imagenet_class_index.txt\", \"r\").read()\n",
+    "    # seperate elements and onvert string to list\n",
+    "    imagenet_labels_raw = imagenet_file.strip().split('\\n')\n",
+    "    # keep first label\n",
+    "    imagenet_labels = [item.split(',')[0] for item in imagenet_labels_raw]\n",
+    "    return imagenet_labels\n",
+    "\n",
+    "imagenet_labels = get_imagenet_classes()\n",
+    "\n",
+    "# Create Model\n",
+    "def create_model(model_name='vgg16.tv_in1k'):\n",
+    "    # import required model\n",
+    "    model = timm.create_model(model_name, pretrained=True).eval()\n",
+    "    # transform data as required by the model\n",
+    "    transform = timm.data.create_transform(\n",
+    "        **timm.data.resolve_data_config(model.pretrained_cfg)\n",
+    "    )\n",
+    "    return model, transform\n",
+    "\n",
+    "model, transform = create_model()\n",
+    "\n",
+    "# Car or Not : Main Inferene Code\n",
+    "catogories = ('Is a Car', 'Not a Car')\n",
+    "def car_or_not_inference(input_image):\n",
+    "\n",
+    "    # print (\"Validating that this is a picture of a car...\")\n",
+    "\n",
+    "    # retain the top 'n' most occuring items \\\\ n=36\n",
+    "    top_n_cat_list  = ['sports_car', 'minivan', 'convertible', 'beach_wagon', 'limousine', 'pickup', 'car_wheel', 'grille', 'racer', 'minibus', 'jeep', 'moving_van', 'tow_truck', 'cab', 'police_van', 'snowplow', 'amphibian', 'trailer_truck', 'recreational_vehicle', 'ambulance', 'motor_scooter', 'cassette_player', 'fire_engine', 'car_mirror', 'mobile_home', 'crash_helmet', 'mouse', 'snowmobile', 'Model_T', 'passenger_car', 'solar_dish', 'garbage_truck', 'photocopier', 'mountain_tent', 'half_track', 'speedboat']\n",
+    "\n",
+    "    # image = PILImage.create(input_image)\n",
+    "    # transform image as required for prediction\n",
+    "    image_tensor = transform(input_image)\n",
+    "    # predict on image\n",
+    "    output = model(image_tensor.unsqueeze(0))\n",
+    "    # get probabilites\n",
+    "    probabilities = torch.nn.functional.softmax(output[0], dim=0)\n",
+    "    # select top 5 probs\n",
+    "    _, indices = torch.topk(probabilities, 5)\n",
+    "\n",
+    "    for idx in indices:\n",
+    "        pred_label = imagenet_labels[idx]\n",
+    "        if pred_label in top_n_cat_list:\n",
+    "            return 1.0 #dict(zip(catogories, [1.0, 0.0])) #\"Validation complete - proceed to damage evaluation\"\n",
+    "\n",
+    "    return 0.0 #dict(zip(catogories, [0.0, 1.0]))#\"Are you sure this is a picture of your car? Please take another picture (try a different angle or lighting) and try again.\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29a9aacc-fcb0-4dd0-a7a9-82d56ceccb3c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# input_image = examples_path+'rolls.jpg'\n",
+    "# car_or_not_inference(input_image)\n",
+    "\n",
+    "# input_image = 'assets/examples/severe.jpg'\n",
+    "# print(predict(input_image, learn_damaged_or_not))\n",
+    "# print(predict(input_image, learn_damage_location))\n",
+    "# print(predict(input_image, learn_damage_severity))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4e40a3a0-ad15-40ae-b4b4-a0afd610bc82",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#|export\n",
+    "\n",
+    "title = \"Car Care\"\n",
+    "description = \"A vision based car damage identifier.\"\n",
+    "examples = [examples_path+'lambo.jpg', examples_path+'dog.jpg', examples_path+'front_moderate.jpg']\n",
+    "\n",
+    "learn_damaged_or_not = load_learner(models_path+'car_damaged_or_not.pkl')\n",
+    "learn_damage_location = load_learner(models_path+'car_damage_side.pkl')\n",
+    "learn_damage_severity = load_learner(models_path+'car_damage_severity.pkl')\n",
+    "\n",
+    "def predict(img, learn):\n",
+    "    # img = PILImage.create(img)\n",
+    "    pred, idx, probs = learn.predict(img)\n",
+    "    return pred#, float(probs[idx])\n",
+    "\n",
+    "def main_predictor(img,  progress=gr.Progress()):\n",
+    "    \n",
+    "    progress((0,4), desc=\"Starting Analysis...\")    \n",
+    "    input_image = PILImage.create(img)\n",
+    "    car_or_not = car_or_not_inference(input_image)\n",
+    "\n",
+    "    progress((1,4))\n",
+    "    if car_or_not:\n",
+    "        gr.Info(\"Car check completed.\")\n",
+    "        damaged_or_not = predict(input_image, learn_damaged_or_not)\n",
+    "\n",
+    "        progress((2,4))\n",
+    "        if damaged_or_not == 'damage':\n",
+    "            gr.Info(\"Damage check completed.\")\n",
+    "            damaged_location = predict(input_image, learn_damage_location)\n",
+    "            progress((3,4))\n",
+    "            gr.Info(\"Damage Location identified.\")\n",
+    "            damaged_severity = predict(input_image, learn_damage_severity)\n",
+    "            progress((4,4), desc=\"Analysis Complete\")\n",
+    "            gr.Info(\"Damage Severity assessed.\")\n",
+    "            # refer below sections for Location and Severity\n",
+    "            return f\"\"\"Results: \\n Car Check: it's a Car \\n Damage Check: Car is Damaged \\n Location: {damaged_location} \\n Severity: {damaged_severity}\"\"\"\n",
+    "        else:\n",
+    "            progress((4,4))\n",
+    "            return \"Are you sure your car is damaged ?. \\nMake sure you click a clear picture of the damaged portion. \\nPlease resubmit the picture\"\n",
+    "    else:\n",
+    "        progress((4,4))\n",
+    "        return \"Are you sure this is a picture of your car? \\nPlease take another picture (try a different angle or lighting) and try again.\"\n",
+    "\n",
+    "# input_image = 'assets/examples/severe.jpg'\n",
+    "# main_predictor(input_image)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0955b1fb-5216-464a-bc30-618751136fc6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "Could not create share link. Please check your internet connection or our status page: https://status.gradio.app.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#|export\n",
+    "intf = gr.Interface(fn=main_predictor,inputs=gr.Image(),outputs=gr.Textbox(),title=title,description=description,examples=examples)\n",
+    "intf.launch(share=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19a074b9-9edf-441b-8ff9-8fb91fd07952",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nbdev\n",
+    "nbdev.export.nb_export('car_damage_detector.ipynb','.')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "416c2277-fac4-4cee-9adb-7fc80026ca2a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "384b395a-20fa-4c3c-a8a5-fd0a4e529a51",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e39de30a-d5b5-4140-9dde-9e84b7510eef",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Loaded as API: https://suku9-car-damage-detection.hf.space ✔\n",
+      "Are you sure this is a picture of your car? \n",
+      "Please take another picture (try a different angle or lighting) and try again.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from gradio_client import Client, file\n",
+    "client = Client(\"suku9/Car_Damage_Detection\")\n",
+    "\n",
+    "input_image = 'assets/examples/dog.jpg'\n",
+    "res = client.predict(file(input_image),api_name=\"/predict\")\n",
+    "print(res)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "963bf22b-3280-4d0a-ab2e-9c189b9705e4",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ebd92af9-434c-4433-ac71-263e18bf66d0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "python3",
+   "language": "python",
+   "name": "python3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}