{"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":"none","dataSources":[{"sourceId":16017,"databundleVersionId":708189,"sourceType":"competition"}],"dockerImageVersionId":30587,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# 1. Import Libraries","metadata":{}},{"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","execution":{"iopub.status.busy":"2023-12-08T13:15:42.524681Z","iopub.execute_input":"2023-12-08T13:15:42.525743Z","iopub.status.idle":"2023-12-08T13:15:42.534159Z","shell.execute_reply.started":"2023-12-08T13:15:42.525687Z","shell.execute_reply":"2023-12-08T13:15:42.532488Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 2. Define Custom dataset class","metadata":{}},{"cell_type":"code","source":"class TrainMNIST(Dataset):\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        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\n        ","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:15:42.537633Z","iopub.execute_input":"2023-12-08T13:15:42.538172Z","iopub.status.idle":"2023-12-08T13:15:42.549239Z","shell.execute_reply.started":"2023-12-08T13:15:42.538129Z","shell.execute_reply":"2023-12-08T13:15:42.547927Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class TestMNIST(Dataset):\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        image = self.data.iloc[index, 1:].values.astype(np.uint8).reshape((28, 28))\n        \n        if self.transform is not None:\n            image = self.transform(image)\n            \n        return image                                                 ","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:15:42.551096Z","iopub.execute_input":"2023-12-08T13:15:42.551506Z","iopub.status.idle":"2023-12-08T13:15:42.566906Z","shell.execute_reply.started":"2023-12-08T13:15:42.551462Z","shell.execute_reply":"2023-12-08T13:15:42.565735Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 3. Load and Visualize the Data","metadata":{}},{"cell_type":"code","source":"train_dataset = TrainMNIST('/kaggle/input/Kannada-MNIST/train.csv', transform = transforms.ToTensor())\ntest_dataset = TestMNIST('/kaggle/input/Kannada-MNIST/test.csv', transform = transforms.ToTensor())","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:15:42.570138Z","iopub.execute_input":"2023-12-08T13:15:42.571291Z","iopub.status.idle":"2023-12-08T13:15:47.540369Z","shell.execute_reply.started":"2023-12-08T13:15:42.571249Z","shell.execute_reply":"2023-12-08T13:15:47.538848Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_workers = 0\n\nbatch_size = 32\n\ntrain_loader = torch.utils.data.DataLoader(train_dataset, batch_size = batch_size, num_workers = num_workers)\ntest_loader = torch.utils.data.DataLoader(test_dataset, batch_size = batch_size, num_workers = num_workers)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:15:47.541802Z","iopub.execute_input":"2023-12-08T13:15:47.542204Z","iopub.status.idle":"2023-12-08T13:15:47.549771Z","shell.execute_reply.started":"2023-12-08T13:15:47.542170Z","shell.execute_reply":"2023-12-08T13:15:47.548530Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2023-12-08T13:15:47.551954Z","iopub.execute_input":"2023-12-08T13:15:47.552762Z","iopub.status.idle":"2023-12-08T13:15:48.831797Z","shell.execute_reply.started":"2023-12-08T13:15:47.552717Z","shell.execute_reply":"2023-12-08T13:15:48.830542Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 4. Neural Network Design","metadata":{}},{"cell_type":"code","source":"import torch.nn as nn\nimport torch.nn.functional as F\n\nclass NN(nn.Module):\n    def __init__(self):\n        super(NN, 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 = NN()\nprint(model)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:15:48.833651Z","iopub.execute_input":"2023-12-08T13:15:48.834393Z","iopub.status.idle":"2023-12-08T13:15:48.853117Z","shell.execute_reply.started":"2023-12-08T13:15:48.834351Z","shell.execute_reply":"2023-12-08T13:15:48.851849Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 5. Choose Loss Function & Optimizer","metadata":{}},{"cell_type":"code","source":"criterion = nn.CrossEntropyLoss()\n\noptimizer = torch.optim.SGD(model.parameters(), lr=0.01)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:15:48.854951Z","iopub.execute_input":"2023-12-08T13:15:48.855716Z","iopub.status.idle":"2023-12-08T13:15:48.864987Z","shell.execute_reply.started":"2023-12-08T13:15:48.855668Z","shell.execute_reply":"2023-12-08T13:15:48.863103Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 6. Train Network","metadata":{}},{"cell_type":"code","source":"n_epochs = 20\n\ntrain_loss_min = np.Inf \n\n# for plot\ntrain_losses = []\nepochs = []\n\nfor epoch in range(n_epochs):\n    train_loss = 0.0\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    # Append training loss and epoch values for plotting\n    train_losses.append(train_loss)\n    epochs.append(epoch + 1)\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\n        \n# Plotting training loss vs. epoch\nplt.figure(figsize=(10, 6))\nplt.plot(epochs, train_losses, linestyle='-', marker='o', markersize=5, label='Training loss', color='green')\nplt.title('Training Loss vs Epochs')\nplt.xlabel('Epochs')\nplt.ylabel('Training Loss')\nplt.legend()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:15:48.869564Z","iopub.execute_input":"2023-12-08T13:15:48.870112Z","iopub.status.idle":"2023-12-08T13:22:47.606660Z","shell.execute_reply.started":"2023-12-08T13:15:48.870063Z","shell.execute_reply":"2023-12-08T13:22:47.605192Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.load_state_dict(torch.load('model.pt'))","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:22:47.608913Z","iopub.execute_input":"2023-12-08T13:22:47.609956Z","iopub.status.idle":"2023-12-08T13:22:47.622544Z","shell.execute_reply.started":"2023-12-08T13:22:47.609914Z","shell.execute_reply":"2023-12-08T13:22:47.620234Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 7. Visualize Sample Test Results","metadata":{}},{"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(str(labels[idx].item()))","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:22:47.624118Z","iopub.execute_input":"2023-12-08T13:22:47.624626Z","iopub.status.idle":"2023-12-08T13:22:48.889165Z","shell.execute_reply.started":"2023-12-08T13:22:47.624584Z","shell.execute_reply":"2023-12-08T13:22:48.887473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 8. Predict digit based on Input","metadata":{}},{"cell_type":"code","source":"test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=1, \n    num_workers=num_workers)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:22:48.890989Z","iopub.execute_input":"2023-12-08T13:22:48.891450Z","iopub.status.idle":"2023-12-08T13:22:48.898921Z","shell.execute_reply.started":"2023-12-08T13:22:48.891397Z","shell.execute_reply":"2023-12-08T13:22:48.897152Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2023-12-08T13:22:48.900484Z","iopub.execute_input":"2023-12-08T13:22:48.901578Z","iopub.status.idle":"2023-12-08T13:22:48.912945Z","shell.execute_reply.started":"2023-12-08T13:22:48.901525Z","shell.execute_reply":"2023-12-08T13:22:48.911575Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = predict(model,test_loader)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:22:48.915502Z","iopub.execute_input":"2023-12-08T13:22:48.916608Z","iopub.status.idle":"2023-12-08T13:22:52.124432Z","shell.execute_reply.started":"2023-12-08T13:22:48.916565Z","shell.execute_reply":"2023-12-08T13:22:52.123255Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"p = []\nfor a in predictions:\n    p.append(a.item())\n    \npredictions = np.array(p)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:22:52.126047Z","iopub.execute_input":"2023-12-08T13:22:52.126502Z","iopub.status.idle":"2023-12-08T13:22:52.144243Z","shell.execute_reply.started":"2023-12-08T13:22:52.126460Z","shell.execute_reply":"2023-12-08T13:22:52.142559Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data = pd.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\")\n\n\nsubmission = pd.DataFrame(data={\n    \"Id\": test_data.index,\n    \"Label\": p\n})\nsubmission.to_csv(\"submission.csv\", index=None)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T13:22:52.146822Z","iopub.execute_input":"2023-12-08T13:22:52.148076Z","iopub.status.idle":"2023-12-08T13:22:52.572780Z","shell.execute_reply.started":"2023-12-08T13:22:52.148034Z","shell.execute_reply":"2023-12-08T13:22:52.570905Z"},"trusted":true},"execution_count":null,"outputs":[]}]}