{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-10-03T00:10:23.031211Z","iopub.execute_input":"2023-10-03T00:10:23.031658Z","iopub.status.idle":"2023-10-03T00:10:23.342011Z","shell.execute_reply.started":"2023-10-03T00:10:23.031616Z","shell.execute_reply":"2023-10-03T00:10:23.341103Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import 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","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:10:23.343623Z","iopub.execute_input":"2023-10-03T00:10:23.344021Z","iopub.status.idle":"2023-10-03T00:10:27.314498Z","shell.execute_reply.started":"2023-10-03T00:10:23.343990Z","shell.execute_reply":"2023-10-03T00:10:27.313578Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2023-10-03T00:10:27.315743Z","iopub.execute_input":"2023-10-03T00:10:27.316212Z","iopub.status.idle":"2023-10-03T00:10:27.322910Z","shell.execute_reply.started":"2023-10-03T00:10:27.316173Z","shell.execute_reply":"2023-10-03T00:10:27.321771Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class TestMNIST(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    \n        \n        if self.transform is not None:\n            image = self.transform(image)\n            \n        return image","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:10:27.325410Z","iopub.execute_input":"2023-10-03T00:10:27.326354Z","iopub.status.idle":"2023-10-03T00:10:27.334216Z","shell.execute_reply.started":"2023-10-03T00:10:27.326323Z","shell.execute_reply":"2023-10-03T00:10:27.333332Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = TrainMNIST('../input/Kannada-MNIST/train.csv', transform=transforms.ToTensor())\ntest_data = TestMNIST('../input/Kannada-MNIST/test.csv', transform=transforms.ToTensor())","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:10:27.335320Z","iopub.execute_input":"2023-10-03T00:10:27.336296Z","iopub.status.idle":"2023-10-03T00:10:31.195051Z","shell.execute_reply.started":"2023-10-03T00:10:27.336263Z","shell.execute_reply":"2023-10-03T00:10:31.194067Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# number of subprocesses to use for data loading\nnum_workers = 2\n# how many samples per batch to load\nbatch_size = 32\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":{"execution":{"iopub.status.busy":"2023-10-03T00:10:31.196504Z","iopub.execute_input":"2023-10-03T00:10:31.196818Z","iopub.status.idle":"2023-10-03T00:10:31.201992Z","shell.execute_reply.started":"2023-10-03T00:10:31.196789Z","shell.execute_reply":"2023-10-03T00:10:31.201049Z"},"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\n# dataiter = iter(train_loader)\nimages, labels = next(iter(train_loader))\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, 10, 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":"2023-10-03T00:10:31.203377Z","iopub.execute_input":"2023-10-03T00:10:31.203960Z","iopub.status.idle":"2023-10-03T00:10:32.470138Z","shell.execute_reply.started":"2023-10-03T00:10:31.203915Z","shell.execute_reply":"2023-10-03T00:10:32.469208Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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        hidden_3 = 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        self.fc3 = nn.Linear(hidden_2, hidden_3)\n        # linear layer (n_hidden -> 10)\n        self.fc4 = nn.Linear(hidden_3, 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        x = F.relu(self.fc3(x))\n        # add output layer\n        x = self.fc4(x)\n        return x\n\n# initialize the NN\nmodel = Net()\nprint(model)","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:10:32.471633Z","iopub.execute_input":"2023-10-03T00:10:32.472525Z","iopub.status.idle":"2023-10-03T00:10:32.489369Z","shell.execute_reply.started":"2023-10-03T00:10:32.472489Z","shell.execute_reply":"2023-10-03T00:10:32.488313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2023-10-03T00:10:32.490825Z","iopub.execute_input":"2023-10-03T00:10:32.491154Z","iopub.status.idle":"2023-10-03T00:10:32.497010Z","shell.execute_reply.started":"2023-10-03T00:10:32.491103Z","shell.execute_reply":"2023-10-03T00:10:32.496091Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# number of epochs to train the model\nn_epochs = 25\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":{"execution":{"iopub.status.busy":"2023-10-03T00:10:32.500596Z","iopub.execute_input":"2023-10-03T00:10:32.500888Z","iopub.status.idle":"2023-10-03T00:17:20.921142Z","shell.execute_reply.started":"2023-10-03T00:10:32.500867Z","shell.execute_reply":"2023-10-03T00:17:20.919867Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.load_state_dict(torch.load('model.pt'))","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:17:20.923149Z","iopub.execute_input":"2023-10-03T00:17:20.923548Z","iopub.status.idle":"2023-10-03T00:17:20.934563Z","shell.execute_reply.started":"2023-10-03T00:17:20.923507Z","shell.execute_reply":"2023-10-03T00:17:20.933483Z"},"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().item())\n#     return prediction_list","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:17:20.935779Z","iopub.execute_input":"2023-10-03T00:17:20.936146Z","iopub.status.idle":"2023-10-03T00:17:20.943738Z","shell.execute_reply.started":"2023-10-03T00:17:20.936115Z","shell.execute_reply":"2023-10-03T00:17:20.942763Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def predict(model, dataloader):\n    model.eval()\n    test_pred = torch.LongTensor()\n    \n    for i, data in enumerate(dataloader):\n#         data = data.cuda()\n        output = model(data)\n        \n        pred = output.cpu().data.max(1, keepdim=True)[1]\n        test_pred = torch.cat((test_pred, pred), dim=0)\n        \n    return test_pred","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:19:48.996367Z","iopub.execute_input":"2023-10-03T00:19:48.996765Z","iopub.status.idle":"2023-10-03T00:19:49.002475Z","shell.execute_reply.started":"2023-10-03T00:19:48.996732Z","shell.execute_reply":"2023-10-03T00:19:49.001473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = predict(model,test_loader)\npredictions = np.array(predictions)","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:19:51.648776Z","iopub.execute_input":"2023-10-03T00:19:51.649805Z","iopub.status.idle":"2023-10-03T00:19:53.089315Z","shell.execute_reply.started":"2023-10-03T00:19:51.649759Z","shell.execute_reply":"2023-10-03T00:19:53.087945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame(data={\n    \"id\": test_data.data.index,\n    \"label\": predictions.flatten()\n})\nsubmission.to_csv(\"submission.csv\", index=None)","metadata":{"execution":{"iopub.status.busy":"2023-10-03T00:21:05.988265Z","iopub.execute_input":"2023-10-03T00:21:05.988617Z","iopub.status.idle":"2023-10-03T00:21:06.003875Z","shell.execute_reply.started":"2023-10-03T00:21:05.988590Z","shell.execute_reply":"2023-10-03T00:21:06.002824Z"},"trusted":true},"execution_count":null,"outputs":[]}]}