Spaces:
Sleeping
Sleeping
File size: 6,967 Bytes
fc055d6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"import torch.nn as nn\n",
"import torch.optim as optim\n",
"from torch.utils.data import Dataset, DataLoader, Subset\n",
"from torchvision import transforms, datasets\n",
"import os\n",
"from PIL import Image\n",
"from tqdm.auto import tqdm\n",
"import torch.nn.functional as F"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"\n",
"class CNN(nn.Module):\n",
" def __init__(self):\n",
" super(CNN, self).__init__()\n",
" # Convolutional layers\n",
" self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1)\n",
" self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)\n",
" self.conv3 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)\n",
" \n",
" # Pooling layer\n",
" self.pool = nn.MaxPool2d(kernel_size=2, stride=2, padding=0)\n",
" \n",
" # Fully connected layers\n",
" self.fc1 = nn.Linear(64 * (224 // 8) * (224 // 8), 64) # Adjusted based on pooling layers\n",
" self.fc2 = nn.Linear(64, 2) # 2 classes for binary classification\n",
" \n",
" def forward(self, x):\n",
" # Convolutional layers with relu activation and pooling\n",
" x = self.pool(F.relu(self.conv1(x)))\n",
" x = self.pool(F.relu(self.conv2(x)))\n",
" x = self.pool(F.relu(self.conv3(x)))\n",
" \n",
" # Flatten for fully connected layers\n",
" x = torch.flatten(x, 1)\n",
" \n",
" # Fully connected layers with relu activation\n",
" x = F.relu(self.fc1(x))\n",
" x = self.fc2(x)\n",
" \n",
" return x"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"transform = transforms.Compose([\n",
" transforms.Resize((224, 224)), # Resize to 224x224\n",
" transforms.ToTensor(), # Convert to tensor\n",
" transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # Normalize\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<All keys matched successfully>"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = CNN()\n",
"\n",
"model.load_state_dict(torch.load(\"trained-cnn-concrete-crack.model\", map_location=torch.device(\"cpu\")))"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [],
"source": [
"\n",
"\n",
"magmaify = colormaps['magma']\n",
"\n",
"\n",
"\n",
"def compute_gradcam(img_tensor, layer_idx):\n",
" target_layers = [[model.conv1], [model.conv2], [model.conv3]]\n",
"\n",
" cam = GradCAM(model=model, target_layers=target_layers[layer_idx-1])\n",
"\n",
" grayscale_cam = cam(input_tensor=img_tensor, targets=None)\n",
"\n",
" return magmaify(grayscale_cam.reshape(224, 224))"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [],
"source": [
"\n",
"def predict_and_gradcam(model, img, layer_idx):\n",
" # Preprocess the image\n",
" img = Image.fromarray(img.astype('uint8'), 'RGB') if isinstance(img, np.ndarray) else img\n",
" img_tensor = transform(img).unsqueeze(0)\n",
"\n",
" # Get predicted class index\n",
" with torch.no_grad():\n",
" output = model(img_tensor)\n",
" _, predicted = torch.max(output.data, 1)\n",
" predicted_label = str(predicted.item())\n",
"\n",
" # Compute GradCAM\n",
" gradcam = compute_gradcam(img_tensor, layer_idx)\n",
"\n",
" return predicted_label, gradcam"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/irsh/miniconda3/envs/speaker_verification/lib/python3.9/site-packages/gradio/interface.py:382: UserWarning: The `allow_flagging` parameter in `Interface` nowtakes a string value ('auto', 'manual', or 'never'), not a boolean. Setting parameter to: 'never'.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7871\n",
"\n",
"To create a public link, set `share=True` in `launch()`.\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7871/\" 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": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"\n",
"idx_to_lbl = {\"0\": \"Cracked\", \"1\":\"Uncracked\"}\n",
"\n",
"# Define a function to be used in Gradio app\n",
"def classify_image(image, layer_idx):\n",
" \n",
" # Predict label and get GradCAM\n",
" label, gradcam_img = predict_and_gradcam(model, image, layer_idx)\n",
"\n",
" return idx_to_lbl[label], gradcam_img\n",
"\n",
"# Define Gradio interface\n",
"iface = gr.Interface(\n",
" fn=classify_image,\n",
" inputs=[gr.Image(), gr.Slider(minimum=1, maximum=3, step=1, value=1)],\n",
" outputs=[gr.Textbox(label=\"Predicted Label\"), gr.Image(label=\"GradCAM Heatmap\")],\n",
" title=\"Concrete Crack Detection with GradCAM\",\n",
" description=\"Upload an image of concrete and get the predicted label along with the GradCAM heatmap.\",\n",
" allow_flagging=False\n",
")\n",
"\n",
"# Launch the interface\n",
"iface.launch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python-3.12",
"language": "python",
"name": "python-3.12"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.19"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|