{"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":"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":{"execution":{"iopub.status.busy":"2023-12-08T15:57:49.590207Z","iopub.execute_input":"2023-12-08T15:57:49.591307Z","iopub.status.idle":"2023-12-08T15:57:49.597687Z","shell.execute_reply.started":"2023-12-08T15:57:49.591261Z","shell.execute_reply":"2023-12-08T15:57:49.596687Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class TrainKannada(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        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":"2023-12-08T15:58:02.514151Z","iopub.execute_input":"2023-12-08T15:58:02.514856Z","iopub.status.idle":"2023-12-08T15:58:02.521611Z","shell.execute_reply.started":"2023-12-08T15:58:02.514825Z","shell.execute_reply":"2023-12-08T15:58:02.520664Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class TestKannada(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        image = self.data.iloc[index, 1:].values.astype(np.uint8).reshape((28, 28, 1))\n        \n        if self.transform is not None:\n            image = self.transform(image)\n            \n        return image","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:58:07.445973Z","iopub.execute_input":"2023-12-08T15:58:07.446337Z","iopub.status.idle":"2023-12-08T15:58:07.453296Z","shell.execute_reply.started":"2023-12-08T15:58:07.446308Z","shell.execute_reply":"2023-12-08T15:58:07.452189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = TrainKannada('/kaggle/input/Kannada-MNIST/train.csv', transform = transforms.ToTensor())\ntest_data = TestKannada('/kaggle/input/Kannada-MNIST/test.csv', transform = transforms.ToTensor())","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:43:17.352508Z","iopub.execute_input":"2023-12-08T15:43:17.353100Z","iopub.status.idle":"2023-12-08T15:43:23.106275Z","shell.execute_reply.started":"2023-12-08T15:43:17.353054Z","shell.execute_reply":"2023-12-08T15:43:23.105077Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_workers = 0\n\nbatch_size = 20\n\n\ntrain_loader = torch.utils.data.DataLoader(train_data, batch_size = batch_size, num_workers = num_workers)\ntest_loader = torch.utils.data.DataLoader(test_data, batch_size = batch_size, num_workers = num_workers)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:43:23.109669Z","iopub.execute_input":"2023-12-08T15:43:23.110060Z","iopub.status.idle":"2023-12-08T15:43:23.694402Z","shell.execute_reply.started":"2023-12-08T15:43:23.110025Z","shell.execute_reply":"2023-12-08T15:43:23.693190Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n%matplotlib inline\n\n\ndataiter = iter(train_loader)\nimages, labels = next(dataiter)\nimages = images.numpy()\n\n\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":"2023-12-08T15:43:23.696046Z","iopub.execute_input":"2023-12-08T15:43:23.697092Z","iopub.status.idle":"2023-12-08T15:43:24.991538Z","shell.execute_reply.started":"2023-12-08T15:43:23.697051Z","shell.execute_reply":"2023-12-08T15:43:24.989960Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch.nn as nn\nimport torch.nn.functional as F\n\n\nclass Net(nn.Module):\n    def __init__(self):\n        super(Net, self).__init__()\n        \n        hidden_1 = 512\n        hidden_2 = 512\n        \n        self.fc1 = nn.Linear(28 * 28, hidden_1)\n        self.fc2 = nn.Linear(hidden_1, hidden_2)\n        self.fc3 = nn.Linear(hidden_2, 10)\n        \n    def forward(self, x):\n        x = x.view(-1, 28 * 28)\n        x = F.relu(self.fc1(x))\n        x = F.relu(self.fc2(x))\n        x = self.fc3(x)\n        \n        return x\n    \nmodel = Net()\nprint(model)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:43:24.993597Z","iopub.execute_input":"2023-12-08T15:43:24.995115Z","iopub.status.idle":"2023-12-08T15:43:25.017360Z","shell.execute_reply.started":"2023-12-08T15:43:24.995066Z","shell.execute_reply":"2023-12-08T15:43:25.016271Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"criterion = nn.CrossEntropyLoss()\n\noptimizer = torch.optim.SGD(model.parameters(), lr = 0.01)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:43:25.018614Z","iopub.execute_input":"2023-12-08T15:43:25.018982Z","iopub.status.idle":"2023-12-08T15:43:25.024644Z","shell.execute_reply.started":"2023-12-08T15:43:25.018950Z","shell.execute_reply":"2023-12-08T15:43:25.023733Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"n_epochs = 20\n\ntrain_loss_min = np.Inf\n\nfor epoch in range(n_epochs):\n    train_loss = 0.0\n    \n    model.train()\n    for data, target in train_loader:\n        optimizer.zero_grad()\n        \n        output= model(data)\n        \n        loss = criterion(output, target)\n        \n        loss.backward()\n        \n        optimizer.step()\n        \n        train_loss += loss.item() * data.size(0)\n        \n    train_loss = train_loss/len(train_loader.dataset)\n    \n    print('Epoch: {} \\tTraining Loss: {:.6f}'.format(epoch + 1, train_loss))\n    \n    \n    if train_loss <= train_loss_min:\n        print(\"Training loss decreased ({:.6f} --> {:.6f}). Saving model ...\".format(train_loss_min, train_loss))\n        torch.save(model.state_dict(), 'model.pt')\n        train_loss_min = train_loss","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:43:25.025733Z","iopub.execute_input":"2023-12-08T15:43:25.026586Z","iopub.status.idle":"2023-12-08T15:51:04.545638Z","shell.execute_reply.started":"2023-12-08T15:43:25.026551Z","shell.execute_reply":"2023-12-08T15:51:04.544233Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.load_state_dict(torch.load('model.pt'))","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:56:21.785677Z","iopub.execute_input":"2023-12-08T15:56:21.786100Z","iopub.status.idle":"2023-12-08T15:56:21.800758Z","shell.execute_reply.started":"2023-12-08T15:56:21.786068Z","shell.execute_reply":"2023-12-08T15:56:21.799648Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataiter = iter(test_loader)\nimages = next(dataiter)\n\noutput = model(images)\n\n_, preds = torch.max(output, 1)\n\nimages = images.numpy()\n\n\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":{"execution":{"iopub.status.busy":"2023-12-08T15:56:55.770757Z","iopub.execute_input":"2023-12-08T15:56:55.771299Z","iopub.status.idle":"2023-12-08T15:56:56.033825Z","shell.execute_reply.started":"2023-12-08T15:56:55.771270Z","shell.execute_reply":"2023-12-08T15:56:56.032718Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_loader = torch.utils.data.DataLoader(test_data, batch_size=1, num_workers=num_workers)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:51:05.890952Z","iopub.execute_input":"2023-12-08T15:51:05.891446Z","iopub.status.idle":"2023-12-08T15:51:05.897394Z","shell.execute_reply.started":"2023-12-08T15:51:05.891401Z","shell.execute_reply":"2023-12-08T15:51:05.896382Z"},"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":"2023-12-08T15:51:05.899132Z","iopub.execute_input":"2023-12-08T15:51:05.899993Z","iopub.status.idle":"2023-12-08T15:51:05.909759Z","shell.execute_reply.started":"2023-12-08T15:51:05.899955Z","shell.execute_reply":"2023-12-08T15:51:05.908336Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = predict(model,test_loader)\n\np = []\nfor a in predictions:\n    p.append(a.item())\n    \np = np.array(p)","metadata":{"execution":{"iopub.status.busy":"2023-12-08T15:51:05.913877Z","iopub.execute_input":"2023-12-08T15:51:05.914297Z","iopub.status.idle":"2023-12-08T15:51:08.949554Z","shell.execute_reply.started":"2023-12-08T15:51:05.914260Z","shell.execute_reply":"2023-12-08T15:51:08.948279Z"},"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":"2023-12-09T02:19:57.206672Z","iopub.execute_input":"2023-12-09T02:19:57.207074Z","iopub.status.idle":"2023-12-09T02:19:57.689965Z","shell.execute_reply.started":"2023-12-09T02:19:57.207034Z","shell.execute_reply":"2023-12-09T02:19:57.688295Z"},"trusted":true},"execution_count":null,"outputs":[]}]}