ResNet_Segmentation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import segmentation_models_pytorch as smp\n",
    "from segmentation_models_pytorch.losses import DiceLoss\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "from torchvision import transforms\n",
    "from PIL import Image\n",
    "import os\n",
    "import numpy as np\n",
    "import torch.optim as optim\n",
    "from tqdm import tqdm\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "from sklearn.metrics import classification_report"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "class FloodAreSegmentation(Dataset):\n",
    "    def __init__(self, data_dir, transform=None):\n",
    "        self.data_dir = data_dir\n",
    "        self.transform = transform\n",
    "        self.image_list = [f for f in os.listdir(os.path.join(data_dir, 'Image')) if f.endswith('.jpg')]\n",
    "\n",
    "    def __len__(self):\n",
    "        return len(self.image_list)\n",
    "\n",
    "    def __getitem__(self, idx):\n",
    "        image_name = self.image_list[idx]\n",
    "        image_path = os.path.join(self.data_dir, 'Image', image_name)\n",
    "        mask_name = os.path.splitext(image_name)[0] + '.png'\n",
    "        mask_path = os.path.join(self.data_dir, 'Mask', mask_name)\n",
    "\n",
    "        image = Image.open(image_path).convert('RGB')\n",
    "        mask = Image.open(mask_path).convert('L')\n",
    "\n",
    "        if self.transform:\n",
    "            image = self.transform(image)\n",
    "            mask = self.transform(mask)\n",
    "\n",
    "        return image, mask\n",
    "\n",
    "\n",
    "data_transforms = transforms.Compose([\n",
    "    transforms.Resize((256, 256)),\n",
    "    transforms.ToTensor()\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_dir = 'flood-area-segmentation'\n",
    "dataset = FloodAreSegmentation(data_dir, transform=data_transforms)\n",
    "dataloader = DataLoader(dataset, batch_size=4, shuffle=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "ENCODER='resnet18'\n",
    "WEIGHTS='imagenet'\n",
    "\n",
    "class SegmentationModel(nn.Module):\n",
    "    def __init__(self):\n",
    "        super(SegmentationModel,self).__init__()\n",
    "\n",
    "        self.arc=smp.Unet(\n",
    "            encoder_name=ENCODER,\n",
    "            encoder_weights=WEIGHTS,\n",
    "            in_channels=3,\n",
    "            classes=1,\n",
    "            activation=None\n",
    "        )\n",
    "    def forward(self,images,masks=None):\n",
    "        logits=self.arc(images)\n",
    "\n",
    "        if masks!=None:\n",
    "            loss1=DiceLoss(mode='binary')(logits,masks)\n",
    "            loss2=nn.BCEWithLogitsLoss()(logits,masks)\n",
    "            return logits,loss1,loss2\n",
    "        return logits"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SegmentationModel(\n",
       "  (arc): Unet(\n",
       "    (encoder): ResNetEncoder(\n",
       "      (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
       "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "      (relu): ReLU(inplace=True)\n",
       "      (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
       "      (layer1): Sequential(\n",
       "        (0): BasicBlock(\n",
       "          (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "        )\n",
       "        (1): BasicBlock(\n",
       "          (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "        )\n",
       "      )\n",
       "      (layer2): Sequential(\n",
       "        (0): BasicBlock(\n",
       "          (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
       "          (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (downsample): Sequential(\n",
       "            (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
       "            (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          )\n",
       "        )\n",
       "        (1): BasicBlock(\n",
       "          (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "        )\n",
       "      )\n",
       "      (layer3): Sequential(\n",
       "        (0): BasicBlock(\n",
       "          (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
       "          (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (downsample): Sequential(\n",
       "            (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
       "            (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          )\n",
       "        )\n",
       "        (1): BasicBlock(\n",
       "          (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "        )\n",
       "      )\n",
       "      (layer4): Sequential(\n",
       "        (0): BasicBlock(\n",
       "          (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
       "          (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (downsample): Sequential(\n",
       "            (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
       "            (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          )\n",
       "        )\n",
       "        (1): BasicBlock(\n",
       "          (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "        )\n",
       "      )\n",
       "    )\n",
       "    (decoder): UnetDecoder(\n",
       "      (center): Identity()\n",
       "      (blocks): ModuleList(\n",
       "        (0): DecoderBlock(\n",
       "          (conv1): Conv2dReLU(\n",
       "            (0): Conv2d(768, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention1): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "          (conv2): Conv2dReLU(\n",
       "            (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention2): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "        )\n",
       "        (1): DecoderBlock(\n",
       "          (conv1): Conv2dReLU(\n",
       "            (0): Conv2d(384, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention1): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "          (conv2): Conv2dReLU(\n",
       "            (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention2): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "        )\n",
       "        (2): DecoderBlock(\n",
       "          (conv1): Conv2dReLU(\n",
       "            (0): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention1): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "          (conv2): Conv2dReLU(\n",
       "            (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention2): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "        )\n",
       "        (3): DecoderBlock(\n",
       "          (conv1): Conv2dReLU(\n",
       "            (0): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention1): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "          (conv2): Conv2dReLU(\n",
       "            (0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention2): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "        )\n",
       "        (4): DecoderBlock(\n",
       "          (conv1): Conv2dReLU(\n",
       "            (0): Conv2d(32, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention1): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "          (conv2): Conv2dReLU(\n",
       "            (0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "            (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "            (2): ReLU(inplace=True)\n",
       "          )\n",
       "          (attention2): Attention(\n",
       "            (attention): Identity()\n",
       "          )\n",
       "        )\n",
       "      )\n",
       "    )\n",
       "    (segmentation_head): SegmentationHead(\n",
       "      (0): Conv2d(16, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
       "      (1): Identity()\n",
       "      (2): Activation(\n",
       "        (activation): Identity()\n",
       "      )\n",
       "    )\n",
       "  )\n",
       ")"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "use_cuda = torch.cuda.is_available()\n",
    "\n",
    "device = torch.device(\"cuda\" if use_cuda else \"cpu\")\n",
    "\n",
    "segmentation_model = SegmentationModel()\n",
    "segmentation_model.load_state_dict(torch.load(\"Inference/segmentation_model.pt\"))\n",
    "segmentation_model.to(device)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# define the loss function\n",
    "criterion = nn.BCEWithLogitsLoss()\n",
    "\n",
    "# define the optimizer\n",
    "optimizer = optim.Adam(segmentation_model.parameters(), lr=0.001)\n",
    "\n",
    "# define the number of epochs to train for\n",
    "num_epochs = 100\n",
    "\n",
    "for epoch in range(num_epochs):\n",
    "    running_loss = 0.0\n",
    "    correct = 0\n",
    "    total = 0\n",
    "\n",
    "    # create a progress bar using tqdm\n",
    "    pbar = tqdm(enumerate(dataloader), total=len(dataloader))\n",
    "    for i, data in pbar:\n",
    "        # get the inputs and labels and move them to the GPU\n",
    "        inputs, labels = data\n",
    "\n",
    "        inputs = inputs.to(device)\n",
    "        labels = labels.to(device)\n",
    "\n",
    "        # zero the parameter gradients\n",
    "        optimizer.zero_grad()\n",
    "\n",
    "        # forward pass\n",
    "        outputs = segmentation_model(inputs)\n",
    "        loss = criterion(outputs, labels)\n",
    "\n",
    "        # compute the accuracy\n",
    "        predicted = outputs > 0.5\n",
    "        total += labels.numel()\n",
    "        correct += (predicted == labels).sum().item()\n",
    "\n",
    "        # backward pass\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "\n",
    "        # update the progress bar and print statistics\n",
    "        running_loss += loss.item()\n",
    "        pbar.set_description(f'Epoch: {epoch + 1}, Loss: {running_loss / (i + 1):.3f}, Accuracy: {correct / total:.3f}')\n",
    "\n",
    "\n",
    "print('Finished Training')"
   ]
  }
 ],
 "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": "3.8.5"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "0eefc6a63c6d719296cee5685f23fefb92aa63e2e9fdaf52ddbdc4ce266c7bb3"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}