{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":3362,"databundleVersionId":31148}],"dockerImageVersionId":31286,"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":"2026-03-09T11:13:12.463879Z","iopub.execute_input":"2026-03-09T11:13:12.464181Z","iopub.status.idle":"2026-03-09T11:13:12.473646Z","shell.execute_reply.started":"2026-03-09T11:13:12.464154Z","shell.execute_reply":"2026-03-09T11:13:12.472647Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from zipfile import ZipFile\nfrom PIL import Image\n\nimport torch\nimport torch.utils.data as data\nimport torch.optim as optim\nimport torch.nn as nn\n\n\nMEAN_HIGHT = 360\nMEAN_WEIGHT = 400\nBATCH_SIZE = 32\nEPOCH = 5\n\n\nclass MyData(data.Dataset):\n    def __init__(self, train=True):\n        \n        if train:\n            self.myzip = ZipFile('/kaggle/input/competitions/dogs-vs-cats/train.zip')\n        else:\n            self.myzip = ZipFile('/kaggle/input/competitions/dogs-vs-cats/test1.zip')\n            \n        self.archive_members = self.myzip.namelist()[1:]\n        self.lenth = len(self.archive_members)\n        \n    def __len__(self):\n        return self.lenth\n        \n    def __getitem__(self, indx):\n        for num, member in enumerate(self.archive_members):\n            if indx == num:\n                target = 1 if 'dog' in member else 0\n                with self.myzip.open(member) as myfile:\n                    img = Image.open(myfile).resize((MEAN_HIGHT, MEAN_WEIGHT))\n                    array = torch.tensor(np.asarray(img)).to(torch.float32)\n                    return array.permute(2, 1, 0), target\n            \n\nds = MyData()\ntrain = data.DataLoader(ds, shuffle=True, batch_size=BATCH_SIZE, drop_last=True)\n\nsmall_dataset = torch.utils.data.Subset(train.dataset, range(5000))\nsmall_loader = DataLoader(small_dataset, batch_size=BATCH_SIZE, shuffle=True)\n\n'''mean_height, mean_weight = 0, 0\nfor obj, y in train:\n    mean_height += obj.shape[1]\n    mean_weight += obj.shape[2]\n\n\nmean_height = mean_height // len(ds)\nmean_weight = mean_weight // len(ds)\n\nmean_height, mean_weight'''  # 360 404","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:41:33.146682Z","iopub.execute_input":"2026-03-09T11:41:33.147105Z","iopub.status.idle":"2026-03-09T11:41:33.285658Z","shell.execute_reply.started":"2026-03-09T11:41:33.147075Z","shell.execute_reply":"2026-03-09T11:41:33.284847Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class MyCNN(nn.Module):\n    def __init__(self):\n        super().__init__()\n        self.conv = nn.Sequential(\n            nn.Conv2d(3, 32, 3, padding=1),\n            nn.ReLU(),\n            nn.Conv2d(32, 32, 3, padding=1),\n            nn.ReLU(),\n            nn.MaxPool2d(2),\n\n            nn.Conv2d(32, 64, 3, padding=1),\n            nn.ReLU(),\n            nn.Conv2d(64, 64, 3, padding=1),\n            nn.ReLU(),\n            nn.MaxPool2d(2),\n        \n        \n            nn.Conv2d(64, 128, 3, padding=1),\n            nn.ReLU(),\n            nn.Conv2d(128, 128, 3, padding=1),\n            nn.ReLU(),\n            nn.MaxPool2d(2),\n        \n        \n            nn.Conv2d(128, 256, 3, padding=1),\n            nn.ReLU(),\n            nn.Conv2d(256, 256, 3, padding=1),\n            nn.ReLU(),\n            nn.AdaptiveAvgPool2d(1)\n        )\n\n        self.layers = nn.Sequential(\n            nn.Linear(256, 100),\n            nn.BatchNorm1d(100),\n            nn.ReLU(),\n            \n            nn.Linear(100, 50),\n            nn.BatchNorm1d(50),\n            nn.ReLU(),\n            \n            nn.Linear(50, 2)\n        )\n            \n\n    def forward(self, x):\n        x = self.conv(x)\n        x = x.squeeze()\n        return self.layers(x)\n        \n\n\nmodel = MyCNN()\nmodel.train()\n\nloss_func = nn.CrossEntropyLoss()\nadam = optim.Adam(model.parameters())\nfor epoch in range(EPOCH):\n    for x, y in small_loader:\n        predict = model(x)\n        loss = loss_func(predict, y)\n\n        adam.zero_grad()\n        loss.backward()\n        adam.step()\n\n    print(f'EPOCH: {epoch}')\n\n\nmodel.eval()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-09T11:42:22.723108Z","iopub.execute_input":"2026-03-09T11:42:22.723859Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}