{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport os\n\nimport torch\nimport torch.nn as nn\nimport torchvision\nimport torchvision.transforms as transforms\nfrom torch.utils.data import Dataset, DataLoader","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"BATCH = 32\nEPOCHS = 2\nLR = 0.001\n\nDEVICE = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\", dtype=np.float32)\ntest_df = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\", dtype=np.float32)\nsample_sub = pd.read_csv(\"/kaggle/input/digit-recognizer/sample_submission.csv\")\n\ntrain_df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_Train = train_df.label.values\nX0 = train_df.loc[:, train_df.columns != 'label'].values/255\n\nX0.shape, Y_Train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_Train = torch.from_numpy(Y_Train).type(torch.LongTensor)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_Train_1 = X0.reshape((-1, 1, 28, 28))\nX_Train_1.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_Train = np.stack((X_Train_1,)*3, axis=1)\nX_Train = np.squeeze(X_Train, axis=2)\nX_Train.shape\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Transform = transforms.Compose(\n    [transforms.ToTensor()])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class GetData(Dataset):\n    def __init__(self, X_Train, Y_Train, Transform):\n        self.X = X_Train\n        self.transform = Transform\n        self.Y = Y_Train\n        \n    def __len__(self):\n        return len(self.X)\n\n    def __getitem__(self, index):\n        return self.transform(self.X[index]).permute((1, 2, 0)).contiguous(), self.Y[index]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainset = GetData(X_Train, Y_Train, Transform)\ntrainloader = DataLoader(trainset, batch_size=BATCH, shuffle=True, num_workers=4)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"next(iter(trainloader))[0].shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = torchvision.models.resnet152()\nmodel.fc = nn.Linear(2048, 10, bias=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = model.to(DEVICE)\ncriterion = nn.CrossEntropyLoss()\noptimizer = torch.optim.Adam(model.parameters(), lr=LR)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for epoch in range(EPOCHS):\n    tr_loss = 0.0\n\n    model = model.train()\n\n    for i, (images, labels) in enumerate(trainloader):\n        \n        images = images.to(DEVICE)\n        labels = labels.to(DEVICE)\n\n        logits = model(images)\n        loss = criterion(logits, labels)\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n\n        tr_loss += loss.detach().item()\n    \n    model.eval()\n    print('Epoch: %d | Loss: %.4f'%(epoch, tr_loss / i))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Xt_1 = (test_df.values/255).reshape((-1, 1, 28, 28))\nXt_1.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Xt = np.stack((Xt_1,)*3, axis=1)\nXt = np.squeeze(Xt, axis=2)\nXt.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with torch.no_grad():\n    model.eval()\n    sample_sub['Label'] = model(torch.from_numpy(Xt).to(DEVICE)).cpu().argmax(dim=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}