{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":16017,"databundleVersionId":708189,"sourceType":"competition"}],"dockerImageVersionId":30919,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# import libraries\nimport torch\nfrom torch.utils.data import DataLoader, Dataset\nimport torchvision\nimport torchvision.transforms as transforms\nfrom torch.utils.data.sampler import SubsetRandomSampler\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:26:02.416467Z","iopub.execute_input":"2025-02-23T10:26:02.416919Z","iopub.status.idle":"2025-02-23T10:26:02.421542Z","shell.execute_reply.started":"2025-02-23T10:26:02.416877Z","shell.execute_reply":"2025-02-23T10:26:02.420441Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class TrainMNIST(Dataset):\n    \n    def __init__(self, file_path, transform=None):\n        self.data = pd.read_csv(file_path)\n        self.transform = transform\n        \n    def __len__(self):\n        return len(self.data)\n    \n    def __getitem__(self, index):\n        # load image as ndarray type (Height * Width * Channels)\n        # be carefull for converting dtype to np.uint8 [Unsigned integer (0 to 255)]\n        # in this example, we use ToTensor(), so we define the numpy array like (H, W, C)\n        image = self.data.iloc[index, 1:].values.astype(np.uint8).reshape((28, 28, 1))\n        label = self.data.iloc[index, 0]\n        \n        if self.transform is not None:\n            image = self.transform(image)\n            \n        return image, label","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:26:02.422988Z","iopub.execute_input":"2025-02-23T10:26:02.423279Z","iopub.status.idle":"2025-02-23T10:26:02.438189Z","shell.execute_reply.started":"2025-02-23T10:26:02.423231Z","shell.execute_reply":"2025-02-23T10:26:02.437399Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class TestMNIST(Dataset):\n    \n    def __init__(self, file_path, transform=None):\n        self.data = pd.read_csv(file_path, index_col=0)\n        self.transform = transform\n        \n    def __len__(self):\n        return len(self.data)\n    \n    def __getitem__(self, index):\n        # load image as ndarray type (Height * Width * Channels)\n        # be carefull for converting dtype to np.uint8 [Unsigned integer (0 to 255)]\n        # in this example, we use ToTensor(), so we define the numpy array like (H, W, C)\n        image = self.data.iloc[index, 0:].values.astype(np.uint8).reshape((28, 28, 1))\n    \n        \n        if self.transform is not None:\n            image = self.transform(image)\n            \n        return image","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:33:09.199900Z","iopub.execute_input":"2025-02-23T10:33:09.200380Z","iopub.status.idle":"2025-02-23T10:33:09.209393Z","shell.execute_reply.started":"2025-02-23T10:33:09.200340Z","shell.execute_reply":"2025-02-23T10:33:09.208291Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_data = TrainMNIST('/kaggle/input/Kannada-MNIST/train.csv', transform=transforms.ToTensor())\ntest_data = TestMNIST('/kaggle/input/Kannada-MNIST/test.csv', transform=transforms.ToTensor())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:33:11.051955Z","iopub.execute_input":"2025-02-23T10:33:11.052422Z","iopub.status.idle":"2025-02-23T10:33:13.602436Z","shell.execute_reply.started":"2025-02-23T10:33:11.052376Z","shell.execute_reply":"2025-02-23T10:33:13.601705Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# number of subprocesses to use for data loading\nnum_workers = 0\n# how many samples per batch to load\nbatch_size = 20\n\n# convert data to torch.FloatTensor\n#transform = transforms.ToTensor()\n\n\n# prepare data loaders\ntrain_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size,\n     num_workers=num_workers,)\ntest_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size, \n    num_workers=num_workers)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:33:18.099206Z","iopub.execute_input":"2025-02-23T10:33:18.099526Z","iopub.status.idle":"2025-02-23T10:33:18.105705Z","shell.execute_reply.started":"2025-02-23T10:33:18.099501Z","shell.execute_reply":"2025-02-23T10:33:18.104712Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n%matplotlib inline\n    \n# obtain one batch of training images\ndataiter = iter(train_loader)\nimages, labels = next(dataiter)\nimages = images.numpy()\n\n# plot the images in the batch, along with the corresponding labels\nfig = plt.figure(figsize=(25, 4))\nfor idx in np.arange(20):\n    ax = fig.add_subplot(2, int(20/2), idx+1, xticks=[], yticks=[])\n    ax.imshow(np.squeeze(images[idx]), cmap='gray')\n    # print out the correct label for each image\n    # .item() gets the value contained in a Tensor\n    ax.set_title(str(labels[idx].item()))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:26:05.022890Z","iopub.execute_input":"2025-02-23T10:26:05.023207Z","iopub.status.idle":"2025-02-23T10:26:05.886294Z","shell.execute_reply.started":"2025-02-23T10:26:05.023177Z","shell.execute_reply":"2025-02-23T10:26:05.885418Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch.nn as nn\nimport torch.nn.functional as F\n\n# define the NN architecture\nclass Net(nn.Module):\n    def __init__(self):\n        super(Net, self).__init__()\n        # number of hidden nodes in each layer (512)\n        hidden_1 = 512\n        hidden_2 = 512\n        # linear layer (784 -> hidden_1)\n        self.fc1 = nn.Linear(28 * 28, hidden_1)\n        # linear layer (n_hidden -> hidden_2)\n        self.fc2 = nn.Linear(hidden_1, hidden_2)\n        # linear layer (n_hidden -> 10)\n        self.fc3 = nn.Linear(hidden_2, 10)\n\n\n    def forward(self, x):\n        # flatten image input\n        x = x.view(-1, 28 * 28)\n        # add hidden layer, with relu activation function\n        x = F.relu(self.fc1(x))\n        # add hidden layer, with relu activation function\n        x = F.relu(self.fc2(x))\n        # add output layer\n        x = self.fc3(x)\n        return x\n\n# initialize the NN\nmodel = Net()\nprint(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:26:05.887243Z","iopub.execute_input":"2025-02-23T10:26:05.887592Z","iopub.status.idle":"2025-02-23T10:26:05.899319Z","shell.execute_reply.started":"2025-02-23T10:26:05.887560Z","shell.execute_reply":"2025-02-23T10:26:05.898473Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# specify loss function (categorical cross-entropy)\ncriterion = nn.CrossEntropyLoss()\n\n# specify optimizer (stochastic gradient descent) and learning rate = 0.01\noptimizer = torch.optim.SGD(model.parameters(), lr=0.01)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:26:05.901500Z","iopub.execute_input":"2025-02-23T10:26:05.901700Z","iopub.status.idle":"2025-02-23T10:26:05.905517Z","shell.execute_reply.started":"2025-02-23T10:26:05.901682Z","shell.execute_reply":"2025-02-23T10:26:05.904852Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# number of epochs to train the model\nn_epochs = 20\n\n# initialize tracker for minimum validation loss\ntrain_loss_min = np.Inf # set initial \"min\" to infinity\n\nfor epoch in range(n_epochs):\n    # monitor training loss\n    train_loss = 0.0\n    \n    ###################\n    # train the model #\n    ###################\n    model.train() # prep model for training\n    for data, target in train_loader:\n        # clear the gradients of all optimized variables\n        optimizer.zero_grad()\n        # forward pass: compute predicted outputs by passing inputs to the model\n        output = model(data)\n        # calculate the loss\n        loss = criterion(output, target)\n        # backward pass: compute gradient of the loss with respect to model parameters\n        loss.backward()\n        # perform a single optimization step (parameter update)\n        optimizer.step()\n        # update running training loss\n        train_loss += loss.item()*data.size(0)\n        \n   \n    train_loss = train_loss/len(train_loader.dataset)\n    \n    print('Epoch: {} \\tTraining Loss: {:.6f}'.format(\n        epoch+1, \n        train_loss,\n        ))\n    \n    # save model if validation loss has decreased\n    if train_loss <= train_loss_min:\n        print('Training loss decreased ({:.6f} --> {:.6f}).  Saving model ...'.format(\n        train_loss_min,\n        train_loss))\n        torch.save(model.state_dict(), 'model.pt')\n        train_loss_min = train_loss","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:26:05.906709Z","iopub.execute_input":"2025-02-23T10:26:05.907014Z","iopub.status.idle":"2025-02-23T10:31:39.381898Z","shell.execute_reply.started":"2025-02-23T10:26:05.906983Z","shell.execute_reply":"2025-02-23T10:31:39.381091Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.load_state_dict(torch.load('model.pt'))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:31:39.382713Z","iopub.execute_input":"2025-02-23T10:31:39.383174Z","iopub.status.idle":"2025-02-23T10:31:39.391368Z","shell.execute_reply.started":"2025-02-23T10:31:39.383150Z","shell.execute_reply":"2025-02-23T10:31:39.390315Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# obtain one batch of test images\ndataiter = iter(test_loader)\nimages = next(dataiter)\n\n# get sample outputs\noutput = model(images)\n# convert output probabilities to predicted class\n_, preds = torch.max(output, 1)\n# prep images for display\nimages = images.numpy()\n\n# plot the images in the batch, along with predicted and true labels\nfig = plt.figure(figsize=(25, 4))\nfor idx in np.arange(20):\n    ax = fig.add_subplot(2, int(20/2), idx+1, xticks=[], yticks=[])\n    ax.imshow(np.squeeze(images[idx]), cmap='gray')\n    ax.set_title(\"{}\".format(str(preds[idx].item())))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:33:26.168760Z","iopub.execute_input":"2025-02-23T10:33:26.169079Z","iopub.status.idle":"2025-02-23T10:33:27.001213Z","shell.execute_reply.started":"2025-02-23T10:33:26.169051Z","shell.execute_reply":"2025-02-23T10:33:27.000335Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_loader = torch.utils.data.DataLoader(test_data, batch_size=1, \n    num_workers=num_workers)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:33:31.200128Z","iopub.execute_input":"2025-02-23T10:33:31.200426Z","iopub.status.idle":"2025-02-23T10:33:31.204401Z","shell.execute_reply.started":"2025-02-23T10:33:31.200401Z","shell.execute_reply":"2025-02-23T10:33:31.203419Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def predict(model, dataloader):\n    prediction_list = []\n    for i, batch in enumerate(dataloader):\n        outputs = model(batch)\n        _, predicted = torch.max(outputs.data, 1) \n        prediction_list.append(predicted.cpu())\n    return prediction_list","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:33:32.675763Z","iopub.execute_input":"2025-02-23T10:33:32.676045Z","iopub.status.idle":"2025-02-23T10:33:32.680425Z","shell.execute_reply.started":"2025-02-23T10:33:32.676021Z","shell.execute_reply":"2025-02-23T10:33:32.679630Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"predictions = predict(model,test_loader)\npredictions = np.array(predictions)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:33:35.293142Z","iopub.execute_input":"2025-02-23T10:33:35.293470Z","iopub.status.idle":"2025-02-23T10:33:38.416560Z","shell.execute_reply.started":"2025-02-23T10:33:35.293443Z","shell.execute_reply":"2025-02-23T10:33:38.415811Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_data = pd.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\", index_col=0)\n\n\nsubmission = pd.DataFrame(data={\n    \"id\": test_data.index,\n    \"label\": predictions.flatten()\n})\nsubmission.to_csv(\"submission.csv\", index=None)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-23T10:34:40.746172Z","iopub.execute_input":"2025-02-23T10:34:40.746548Z","iopub.status.idle":"2025-02-23T10:34:40.935348Z","shell.execute_reply.started":"2025-02-23T10:34:40.746513Z","shell.execute_reply":"2025-02-23T10:34:40.934341Z"}},"outputs":[],"execution_count":null}]}