{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":13836,"databundleVersionId":1718836,"sourceType":"competition"}],"dockerImageVersionId":31089,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:25:11.447181Z","iopub.execute_input":"2025-08-05T10:25:11.447766Z","iopub.status.idle":"2025-08-05T10:25:44.65725Z","shell.execute_reply.started":"2025-08-05T10:25:11.447742Z","shell.execute_reply":"2025-08-05T10:25:44.656193Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport torch\nimport torch.optim as optim\nimport torch.nn as nn\nfrom torch.utils.data import DataLoader,Dataset\nfrom torchvision import transforms\nimport os\nfrom PIL import Image","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:25:44.658768Z","iopub.execute_input":"2025-08-05T10:25:44.658994Z","iopub.status.idle":"2025-08-05T10:25:44.663502Z","shell.execute_reply.started":"2025-08-05T10:25:44.658976Z","shell.execute_reply":"2025-08-05T10:25:44.662617Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"data=pd.read_csv(\"/kaggle/input/cassava-leaf-disease-classification/train.csv\")\nimagedirectory=\"/kaggle/input/cassava-leaf-disease-classification/train_images\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:25:44.66435Z","iopub.execute_input":"2025-08-05T10:25:44.664868Z","iopub.status.idle":"2025-08-05T10:25:44.713168Z","shell.execute_reply.started":"2025-08-05T10:25:44.664844Z","shell.execute_reply":"2025-08-05T10:25:44.712557Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"transform=transforms.Compose([\n    transforms.Resize((224,224)),\n    transforms.RandomHorizontalFlip(),\n    transforms.RandomVerticalFlip(),\n    transforms.RandomRotation(15),\n    transforms.ColorJitter(\n        brightness=0.2,\n        contrast=0.2,\n        saturation=0.2,\n        hue=0.1\n    ),\n    transforms.ToTensor(),\n    transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))\n])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:48:02.800991Z","iopub.execute_input":"2025-08-05T10:48:02.801307Z","iopub.status.idle":"2025-08-05T10:48:02.809097Z","shell.execute_reply.started":"2025-08-05T10:48:02.801285Z","shell.execute_reply":"2025-08-05T10:48:02.80802Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"data.head(2)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:25:44.720779Z","iopub.execute_input":"2025-08-05T10:25:44.721056Z","iopub.status.idle":"2025-08-05T10:25:44.746215Z","shell.execute_reply.started":"2025-08-05T10:25:44.721035Z","shell.execute_reply":"2025-08-05T10:25:44.745377Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class CassavaDataset(Dataset):\n    def __init__(self,data,imagedirectory,transform=transform):\n        self.data=data\n        self.imagedirectory=imagedirectory\n        self.transform=transform\n\n    def __len__(self):\n        return len(self.data)\n\n    def __getitem__(self,x):\n        image_path=os.path.join(self.imagedirectory,data[\"image_id\"][x])\n        image=Image.open(image_path)\n        image=self.transform(image)\n        ##label part\n        label=self.data.iloc[x][\"label\"]\n        return image,label","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:27:35.952945Z","iopub.execute_input":"2025-08-05T10:27:35.953862Z","iopub.status.idle":"2025-08-05T10:27:35.959609Z","shell.execute_reply.started":"2025-08-05T10:27:35.953834Z","shell.execute_reply":"2025-08-05T10:27:35.958659Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train=CassavaDataset(data,imagedirectory,transform=transform)\ndataloader=DataLoader(train,shuffle=True,batch_size=64)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:27:36.584512Z","iopub.execute_input":"2025-08-05T10:27:36.584811Z","iopub.status.idle":"2025-08-05T10:27:36.58958Z","shell.execute_reply.started":"2025-08-05T10:27:36.584788Z","shell.execute_reply":"2025-08-05T10:27:36.588809Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class TorchModel(nn.Module):\n    def __init__(self):\n        super().__init__()\n        self.conv1=nn.Conv2d(3,32,3,2,1)\n        self.batchnorm1=nn.BatchNorm2d(32)\n        self.conv2=nn.Conv2d(32,64,3,2,1)\n        self.batchnorm2=nn.BatchNorm2d(64)\n        self.conv3=nn.Conv2d(64,128,3,2,1)\n        self.batchnorm3=nn.BatchNorm2d(128)\n        self.dropout=nn.Dropout(p=0.3)\n        self.layer1=nn.ResidualBlock()\n        self.relu=nn.ReLU()\n        self.linear1=nn.Linear(128*28*28,256)\n        self.linear2=nn.Linear(256,5)\n\n    def forward(self,x):\n        x=self.batchnorm1(self.relu(self.conv1(x)))\n        x=self.batchnorm2(self.relu(self.conv2(x)))\n        x=self.batchnorm3(self.relu(self.conv3(x)))\n        x=x.view(x.size(0),-1)\n        x=self.relu(self.linear1(x))\n        x=self.dropout(x)\n        x=self.linear2(x)\n        return x\n    def residual_block(self,x):\n        \n\nmodel=TorchModel()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:48:49.70646Z","iopub.execute_input":"2025-08-05T10:48:49.706777Z","iopub.status.idle":"2025-08-05T10:48:50.144292Z","shell.execute_reply.started":"2025-08-05T10:48:49.706753Z","shell.execute_reply":"2025-08-05T10:48:50.143653Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for epoch in range(3):\n    model.train()\n    running_loss = 0\n    for images, labels in dataloader:\n        optimizer.zero_grad()\n        outputs = model(images)\n        loss = criterion(outputs, labels)\n        loss.backward()\n        optimizer.step()\n        running_loss += loss.item()\n    print(f\"Epoch {epoch+1} loss: {running_loss / len(dataloader):.4f}\")\n\nacc = train_accuracy(model, dataloader)\nprint(f\"Train Accuracy: {acc:.2f}%\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:57:22.768965Z","iopub.execute_input":"2025-08-05T10:57:22.769285Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"criterion=nn.CrossEntropyLoss()\noptimizer=optim.Adam(model.parameters(),lr=0.001)\ndef train_accuracy(model, dataloader):\n    model.eval()  # Değerlendirme moduna al\n    correct = 0\n    total = 0\n\n    with torch.no_grad():  # Gradient hesaplama kapalı\n        for images, labels in dataloader:\n            outputs = model(images)  # Model tahmini\n            _, predicted = torch.max(outputs.data, 1)  # En yüksek olasılıklı sınıf\n            total += labels.size(0)\n            correct += (predicted == labels).sum().item()\n\n    accuracy = 100 * correct / total\n    return accuracy\n\n\ntrain_accuracy(model,dataloader)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-05T10:48:52.772791Z","iopub.execute_input":"2025-08-05T10:48:52.773064Z","iopub.status.idle":"2025-08-05T10:56:11.012053Z","shell.execute_reply.started":"2025-08-05T10:48:52.773046Z","shell.execute_reply":"2025-08-05T10:56:11.011176Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}