File size: 9,943 Bytes
76479e1 | 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 | {
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "5d4984fd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Note: you may need to restart the kernel to use updated packages.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"gradio 5.43.1 requires fastapi<1.0,>=0.115.2, but you have fastapi 0.115.0 which is incompatible.\n",
"gradio 5.43.1 requires pydantic<2.12,>=2.0, but you have pydantic 2.12.5 which is incompatible.\n",
"gradio 5.43.1 requires starlette<1.0,>=0.40.0; sys_platform != \"emscripten\", but you have starlette 0.38.6 which is incompatible.\n"
]
}
],
"source": [
"%pip install -q torch torchvision pillow opencv-python segmentation-models-pytorch albumentations"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "8e934e27",
"metadata": {},
"outputs": [
{
"ename": "OSError",
"evalue": "[WinError 126] The specified module could not be found. Error loading \"c:\\Users\\abhay\\anaconda3\\Lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies.",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mOSError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[2], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorchvision\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mtransforms\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mtransforms\u001b[39;00m\n\u001b[0;32m 3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mPIL\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Image\n",
"File \u001b[1;32mc:\\Users\\abhay\\anaconda3\\Lib\\site-packages\\torch\\__init__.py:148\u001b[0m\n\u001b[0;32m 146\u001b[0m err \u001b[38;5;241m=\u001b[39m ctypes\u001b[38;5;241m.\u001b[39mWinError(ctypes\u001b[38;5;241m.\u001b[39mget_last_error())\n\u001b[0;32m 147\u001b[0m err\u001b[38;5;241m.\u001b[39mstrerror \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m Error loading \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdll\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m or one of its dependencies.\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m--> 148\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m err\n\u001b[0;32m 150\u001b[0m kernel32\u001b[38;5;241m.\u001b[39mSetErrorMode(prev_error_mode)\n\u001b[0;32m 153\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_preload_cuda_deps\u001b[39m(lib_folder, lib_name):\n",
"\u001b[1;31mOSError\u001b[0m: [WinError 126] The specified module could not be found. Error loading \"c:\\Users\\abhay\\anaconda3\\Lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies."
]
}
],
"source": [
"import torch\n",
"import torchvision.transforms as transforms\n",
"from PIL import Image\n",
"import cv2\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import segmentation_models_pytorch as smp\n",
"import albumentations as A\n",
"from albumentations.pytorch import ToTensorV2\n",
"\n",
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"print(\"Using device:\", device)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f37c3d10",
"metadata": {},
"outputs": [],
"source": [
"# ── Load trained model ──────────────────────────────────────────────────────\n",
"MODEL_PATH = \"best_model.pth\" # path to saved weights\n",
"\n",
"model = smp.Unet(\n",
" encoder_name=\"efficientnet-b3\",\n",
" encoder_weights=None, # weights loaded from checkpoint\n",
" in_channels=3,\n",
" classes=1,\n",
" activation=None\n",
")\n",
"model.load_state_dict(torch.load(MODEL_PATH, map_location=device))\n",
"model.to(device)\n",
"model.eval()\n",
"print(\"Model loaded successfully.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c63c88a3",
"metadata": {},
"outputs": [],
"source": [
"# ── Preprocess & run inference ───────────────────────────────────────────────\n",
"IMAGE_PATH = r\"test images\\test 1.png\" # test image\n",
"PATCH_SIZE = 256\n",
"\n",
"transform = A.Compose([\n",
" A.Normalize(mean=(0.485, 0.456, 0.406),\n",
" std=(0.229, 0.224, 0.225)),\n",
" ToTensorV2()\n",
"])\n",
"\n",
"# Load image\n",
"img_bgr = cv2.imread(IMAGE_PATH)\n",
"assert img_bgr is not None, f\"Could not read image: {IMAGE_PATH}\"\n",
"img_rgb = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)\n",
"\n",
"h, w = img_rgb.shape[:2]\n",
"\n",
"# Pad so dimensions are divisible by PATCH_SIZE\n",
"pad_h = (PATCH_SIZE - h % PATCH_SIZE) % PATCH_SIZE\n",
"pad_w = (PATCH_SIZE - w % PATCH_SIZE) % PATCH_SIZE\n",
"img_padded = np.pad(img_rgb, ((0, pad_h), (0, pad_w), (0, 0)), mode='reflect')\n",
"H, W = img_padded.shape[:2]\n",
"\n",
"# Stitch patch predictions into a full mask\n",
"full_mask = np.zeros((H, W), dtype=np.float32)\n",
"\n",
"with torch.no_grad():\n",
" for i in range(0, H, PATCH_SIZE):\n",
" for j in range(0, W, PATCH_SIZE):\n",
" patch = img_padded[i:i+PATCH_SIZE, j:j+PATCH_SIZE]\n",
" tensor = transform(image=patch)[\"image\"].unsqueeze(0).to(device)\n",
" pred = torch.sigmoid(model(tensor)).squeeze().cpu().numpy()\n",
" full_mask[i:i+PATCH_SIZE, j:j+PATCH_SIZE] = pred\n",
"\n",
"# Crop back to original size\n",
"pred_mask = (full_mask[:h, :w] > 0.5).astype(np.uint8)\n",
"print(f\"Inference done. Image size: {h}×{w} | Buildings detected: {pred_mask.sum()>0}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ffbae7d8",
"metadata": {},
"outputs": [],
"source": [
"# ── Zoning mask & illegal building detection ─────────────────────────────────\n",
"# Default zoning: right half is restricted. Modify as needed.\n",
"def create_zoning_mask(shape):\n",
" \"\"\"Returns a binary mask (1 = restricted zone).\"\"\"\n",
" zm = np.zeros(shape, dtype=np.uint8)\n",
" zm[:, shape[1] // 2:] = 1\n",
" return zm\n",
"\n",
"def detect_illegal_buildings(building_mask, zoning_mask):\n",
" num_labels, labels = cv2.connectedComponents(building_mask)\n",
" illegal, legal = [], []\n",
" for lbl in range(1, num_labels):\n",
" pixels = (labels == lbl)\n",
" if (pixels & (zoning_mask == 1)).any():\n",
" illegal.append(lbl)\n",
" else:\n",
" legal.append(lbl)\n",
" return illegal, legal, labels\n",
"\n",
"def overlay_illegal(image_rgb, labels, illegal_buildings):\n",
" out = image_rgb.copy()\n",
" for lbl in illegal_buildings:\n",
" out[labels == lbl] = [255, 0, 0] # red highlight\n",
" return out\n",
"\n",
"zoning_mask = create_zoning_mask(pred_mask.shape)\n",
"illegal, legal, labels = detect_illegal_buildings(pred_mask, zoning_mask)\n",
"overlay = overlay_illegal(img_rgb, labels, illegal)\n",
"\n",
"print(f\"Total buildings : {len(illegal) + len(legal)}\")\n",
"print(f\"Illegal buildings: {len(illegal)}\")\n",
"print(f\"Legal buildings : {len(legal)}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6692053a",
"metadata": {},
"outputs": [],
"source": [
"# ── Visualize results ────────────────────────────────────────────────────────\n",
"fig, axes = plt.subplots(1, 4, figsize=(20, 5))\n",
"\n",
"axes[0].imshow(img_rgb)\n",
"axes[0].set_title(\"Input Image\")\n",
"axes[0].axis(\"off\")\n",
"\n",
"axes[1].imshow(pred_mask, cmap=\"gray\")\n",
"axes[1].set_title(\"Building Mask\")\n",
"axes[1].axis(\"off\")\n",
"\n",
"axes[2].imshow(zoning_mask, cmap=\"gray\")\n",
"axes[2].set_title(\"Zoning Mask\\n(white = restricted)\")\n",
"axes[2].axis(\"off\")\n",
"\n",
"axes[3].imshow(overlay)\n",
"axes[3].set_title(f\"Illegal Buildings (red)\\nIllegal: {len(illegal)} | Legal: {len(legal)}\")\n",
"axes[3].axis(\"off\")\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|