{"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 \nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.optim as optim\n\nimport torchvision\nimport torchvision.transforms as tfms\nimport torchvision.models as models\n\nfrom torch.utils.data import DataLoader, Dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = 'cuda' if torch.cuda.is_available() else 'cpu'\n\nif device == 'cuda':\n    torch.cuda.set_device(0)\n    print(torch.cuda.current_device())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class CharData(Dataset):\n    \n    def __init__(self,\n                 images,\n                 labels=None,\n                 transform=None,\n                ):\n        self.X = images\n        self.y = labels\n        \n        self.transform = transform\n    \n    def __len__(self):\n        return len(self.X)\n\n    def __getitem__(self, idx):\n        img = np.array(self.X.iloc[idx, :], dtype='uint8').reshape([28, 28, 1])\n        if self.transform is not None:\n            img = self.transform(img)\n        \n        if self.y is not None:\n            y = np.zeros(10, dtype='float32')\n            y[self.y.iloc[idx]] = 1\n            return img, y\n        else:\n            return img","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_transform = tfms.Compose([\n    tfms.ToPILImage(),\n    tfms.RandomAffine(degrees=5, translate=(0.1, 0.1), scale=(0.9, 1.1), shear=5),\n    tfms.ToTensor()\n])\n\n# Test data without augmentation\ntest_transform = tfms.Compose([\n    tfms.ToPILImage(),\n    tfms.ToTensor()\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_csv('../input/Kannada-MNIST/train.csv')\ntarget = df_train['label']\ndf_train.drop('label', axis=1, inplace=True)\n\nX_test = pd.read_csv('../input/Kannada-MNIST/test.csv')\nX_test.drop('id', axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_dev, y_train, y_dev = train_test_split(df_train, target, stratify=target, random_state=42, test_size=0.3)\nprint('X_train', len(X_train))\nprint('X_dev', len(X_dev))\nprint('X_test', len(X_test))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = CharData(X_train, y_train, train_transform)\ndev_dataset = CharData(X_dev, y_dev, test_transform)\ntest_dataset = CharData(X_test, transform=test_transform)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 256\n\ntrain_loader = DataLoader(dataset=train_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=4)\ndev_loader = DataLoader(dataset=dev_dataset, batch_size=BATCH_SIZE, shuffle=False, num_workers=4)\ntest_loader = DataLoader(dataset=test_dataset, batch_size=BATCH_SIZE, shuffle=False, num_workers=4)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(nrows=1, ncols=16, figsize=(30,4))\n\nfor batch in train_loader:\n    for i in range(16):\n        ax[i].set_title(batch[1][i].data.numpy().argmax())\n        ax[i].imshow(batch[0][i, 0], cmap='gray')\n    break","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = models.resnet50(pretrained=False)\nmodel","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.conv1 = nn.Conv2d(1, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fc = nn.Linear(2048, 10, bias=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.to(device)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# class CustomModel(nn.Module):\n#     def __init__(self):\n#         super(CustomModel, self).__init__()\n#         self.conv1 = nn.Conv2d(1, 32, kernel_size=3)\n#         self.conv2 = nn.Conv2d(32, 32, kernel_size=3)\n#         self.fc1 = nn.Linear(24*24*32, 128)\n#         self.fc2 = nn.Linear(128, 10)\n        \n#     def forward(self, x):\n#         x = F.relu(self.conv1(x))\n#         x = F.relu(self.conv2(x))\n#         x = torch.flatten(x, start_dim=1)\n#         x = F.relu(self.fc1(x))\n#         return self.fc2(x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# model = CustomModel().to(device)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = optim.Adam(model.parameters())\ncriterion = nn.CrossEntropyLoss()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def train_step(inputs, targets):\n    optimizer.zero_grad()\n    \n    inputs, targets = inputs.to(device), targets.to(device)\n    outputs = model(inputs)\n    loss = criterion(outputs, targets.long().argmax(1))\n    loss.backward()\n    optimizer.step()\n    \n    batch_loss = loss.item()\n    _, predictions = outputs.max(1)  # return values, indices\n    correct = predictions.eq(targets.long().argmax(1)).sum().item()\n    \n    return batch_loss, correct\n\n\ndef test_step(inputs, targets):\n    with torch.no_grad():\n        inputs, targets = inputs.to(device), targets.to(device)\n        outputs = model(inputs)\n        loss = criterion(outputs, targets.long().argmax(1))\n        \n        batch_loss = loss.item()\n        _, predictions = outputs.max(1)\n        correct = predictions.eq(targets.long().argmax(1)).sum().item()\n        \n        return batch_loss, correct","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 10\nbest_acc = 0.\n\nfor epoch in range(EPOCHS):\n    \n    train_loss = 0.\n    train_total = 0\n    train_correct = 0\n    test_loss = 0.\n    test_total = 0\n    test_correct = 0\n    \n    for batch_idx, (inputs, targets) in enumerate(train_loader):\n        batch_loss, correct = train_step(inputs, targets)\n        train_loss += batch_loss\n        train_total += targets.size(0)\n        train_correct += correct\n        \n    for batch_idx, (inputs, targets) in enumerate(dev_loader):\n        batch_loss, correct = test_step(inputs, targets)\n        test_loss += batch_loss\n        test_total += targets.size(0)\n        test_correct += correct\n        \n    test_accuracy = (test_correct/test_total)*100\n        \n    template = 'Epoch {}, Loss: {:.6f}, Accuracy: {:.3f}%, Test Loss: {:.6f}, Test Accuracy: {:.3f}%'\n    print(template.format(epoch+1,\n                          train_loss,\n                          (train_correct/train_total)*100,\n                          test_loss,\n                          test_accuracy))\n    \n    if test_accuracy > best_acc:\n        print(\"new best acc!\")\n        best_acc = test_accuracy","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.eval()\npredictions = []\n\nfor data in (test_loader):\n    data = data.to(device)\n    output = model(data).max(dim=1)[1] # argmax\n    predictions += list(output.data.cpu().numpy())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nsubmission['label'] = predictions\nsubmission.to_csv('submission.csv', index=False)\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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":1}