{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":16017,"databundleVersionId":708189,"sourceType":"competition"}],"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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\n# import numpy as np # linear algebra\n# import 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\n# import os\n# for 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","trusted":true,"execution":{"iopub.status.busy":"2024-12-06T01:40:13.895779Z","iopub.execute_input":"2024-12-06T01:40:13.896058Z","iopub.status.idle":"2024-12-06T01:40:13.917940Z","shell.execute_reply.started":"2024-12-06T01:40:13.896029Z","shell.execute_reply":"2024-12-06T01:40:13.917202Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"1. Importing library","metadata":{}},{"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\nimport numpy as np\nimport pandas as pd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T01:40:13.919047Z","iopub.execute_input":"2024-12-06T01:40:13.919287Z","iopub.status.idle":"2024-12-06T01:40:18.416972Z","shell.execute_reply.started":"2024-12-06T01:40:13.919263Z","shell.execute_reply":"2024-12-06T01:40:18.416065Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"2. Define Custom dataset class","metadata":{}},{"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":"2024-12-06T01:40:18.418134Z","iopub.execute_input":"2024-12-06T01:40:18.418533Z","iopub.status.idle":"2024-12-06T01:40:18.424459Z","shell.execute_reply.started":"2024-12-06T01:40:18.418475Z","shell.execute_reply":"2024-12-06T01:40:18.423621Z"}},"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)\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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T01:40:18.425956Z","iopub.execute_input":"2024-12-06T01:40:18.426210Z","iopub.status.idle":"2024-12-06T01:40:18.448142Z","shell.execute_reply.started":"2024-12-06T01:40:18.426185Z","shell.execute_reply":"2024-12-06T01:40:18.447219Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"3. Load and Visualize the Data","metadata":{}},{"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":"2024-12-06T01:40:18.449197Z","iopub.execute_input":"2024-12-06T01:40:18.449532Z","iopub.status.idle":"2024-12-06T01:40:22.923083Z","shell.execute_reply.started":"2024-12-06T01:40:18.449481Z","shell.execute_reply":"2024-12-06T01:40:22.922141Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# number of subprogress to use for data loading\nnum_workers = 0\n\n# how many samples per batch to load\nbatch_size = 20\n\n# covert data to torch.FloatTensor\n# transform = transform.ToTensor()\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":"2024-12-06T01:40:22.924337Z","iopub.execute_input":"2024-12-06T01:40:22.924803Z","iopub.status.idle":"2024-12-06T01:40:22.930228Z","shell.execute_reply.started":"2024-12-06T01:40:22.924765Z","shell.execute_reply":"2024-12-06T01:40:22.929373Z"}},"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() get the value contained in a Tensor\n    ax.set_title(str(labels[idx].item()))","metadata":{"execution":{"iopub.status.busy":"2024-12-06T01:40:22.931271Z","iopub.execute_input":"2024-12-06T01:40:22.931571Z","iopub.status.idle":"2024-12-06T01:40:23.847850Z","shell.execute_reply.started":"2024-12-06T01:40:22.931538Z","shell.execute_reply":"2024-12-06T01:40:23.846974Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"4 Thiết kế 1 mạng NN đơn giản Architecture","metadata":{}},{"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    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.logsigmoid(self.fc1(x))\n        # add hidden layer, with relu activation function\n        x = F.logsigmoid(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":"2024-12-06T01:40:23.849116Z","iopub.execute_input":"2024-12-06T01:40:23.849804Z","iopub.status.idle":"2024-12-06T01:40:23.865387Z","shell.execute_reply.started":"2024-12-06T01:40:23.849761Z","shell.execute_reply":"2024-12-06T01:40:23.864545Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"5. Chọn Loss Function và Optimizer","metadata":{}},{"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":"2024-12-06T01:40:23.867897Z","iopub.execute_input":"2024-12-06T01:40:23.868398Z","iopub.status.idle":"2024-12-06T01:40:23.872530Z","shell.execute_reply.started":"2024-12-06T01:40:23.868372Z","shell.execute_reply":"2024-12-06T01:40:23.871732Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"6. Train the Network","metadata":{}},{"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":"2024-12-06T01:40:23.873762Z","iopub.execute_input":"2024-12-06T01:40:23.874084Z","iopub.status.idle":"2024-12-06T01:45:59.192127Z","shell.execute_reply.started":"2024-12-06T01:40:23.874049Z","shell.execute_reply":"2024-12-06T01:45:59.190921Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Load the Model with the Lowest Validation Loss","metadata":{}},{"cell_type":"code","source":"model.load_state_dict(torch.load('model.pt'))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T01:45:59.193613Z","iopub.execute_input":"2024-12-06T01:45:59.193975Z","iopub.status.idle":"2024-12-06T01:45:59.204230Z","shell.execute_reply.started":"2024-12-06T01:45:59.193936Z","shell.execute_reply":"2024-12-06T01:45:59.203562Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"#### Test the Trained Network","metadata":{}},{"cell_type":"markdown","source":"#### 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 probabilites 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":"2024-12-06T01:45:59.205025Z","iopub.execute_input":"2024-12-06T01:45:59.205287Z","iopub.status.idle":"2024-12-06T01:46:00.309352Z","shell.execute_reply.started":"2024-12-06T01:45:59.205257Z","shell.execute_reply":"2024-12-06T01:46:00.308462Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"7. Predict digit dựa vào input >> Tạo file submission trong kaggle","metadata":{}},{"cell_type":"code","source":"test_loader = torch.utils.data.DataLoader(test_data, batch_size=1, num_workers=num_workers)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T01:49:00.740277Z","iopub.execute_input":"2024-12-06T01:49:00.740727Z","iopub.status.idle":"2024-12-06T01:49:00.745349Z","shell.execute_reply.started":"2024-12-06T01:49:00.740692Z","shell.execute_reply":"2024-12-06T01:49:00.744386Z"}},"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":"2024-12-06T01:51:41.504438Z","iopub.execute_input":"2024-12-06T01:51:41.505204Z","iopub.status.idle":"2024-12-06T01:51:41.509694Z","shell.execute_reply.started":"2024-12-06T01:51:41.505169Z","shell.execute_reply":"2024-12-06T01:51:41.508813Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"predictions = predict(model, test_loader)\npredictions = np.array(predictions).flatten()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T01:53:17.475074Z","iopub.execute_input":"2024-12-06T01:53:17.475420Z","iopub.status.idle":"2024-12-06T01:53:20.394792Z","shell.execute_reply.started":"2024-12-06T01:53:17.475390Z","shell.execute_reply":"2024-12-06T01:53:20.393757Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_data = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\n\nsubmission = pd.DataFrame(data={\n    \"id\": test_data.index,\n    \"label\": predictions\n})\nsubmission.to_csv(\"submission.csv\", index=None)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T01:53:27.157297Z","iopub.execute_input":"2024-12-06T01:53:27.157656Z","iopub.status.idle":"2024-12-06T01:53:27.362276Z","shell.execute_reply.started":"2024-12-06T01:53:27.157622Z","shell.execute_reply":"2024-12-06T01:53:27.361549Z"}},"outputs":[],"execution_count":null}]}