{"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":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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":{"execution":{"iopub.status.busy":"2024-01-12T14:06:06.113003Z","iopub.execute_input":"2024-01-12T14:06:06.113395Z","iopub.status.idle":"2024-01-12T14:06:06.549978Z","shell.execute_reply.started":"2024-01-12T14:06:06.113361Z","shell.execute_reply":"2024-01-12T14:06:06.548874Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Train a multi layer Perceptron to classify Kannada-MNIST digits\n---\nDataset information: https://www.kaggle.com/competitions/Kannada-MNIST/overview","metadata":{}},{"cell_type":"markdown","source":"### 1. Importing library","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":{"execution":{"iopub.status.busy":"2024-01-12T14:06:06.552123Z","iopub.execute_input":"2024-01-12T14:06:06.552749Z","iopub.status.idle":"2024-01-12T14:06:10.891185Z","shell.execute_reply.started":"2024-01-12T14:06:06.552704Z","shell.execute_reply":"2024-01-12T14:06:10.889899Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-01-12T14:06:17.610871Z","iopub.execute_input":"2024-01-12T14:06:17.611439Z","iopub.status.idle":"2024-01-12T14:06:17.620158Z","shell.execute_reply.started":"2024-01-12T14:06:17.611405Z","shell.execute_reply":"2024-01-12T14:06:17.618661Z"},"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":"2024-01-12T14:06:20.699532Z","iopub.execute_input":"2024-01-12T14:06:20.699988Z","iopub.status.idle":"2024-01-12T14:06:20.707980Z","shell.execute_reply.started":"2024-01-12T14:06:20.699950Z","shell.execute_reply":"2024-01-12T14:06:20.706681Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"---\n### 3. Load and Visualize the [Data](http://pytorch.org/docs/stable/torchvision/datasets.html)\n\nThử dùng 2 class dataset cho 2 tập test và train ở trên để visualize data","metadata":{}},{"cell_type":"code","source":"train_data = TrainMNIST('/kaggle/input/Kannada-MNIST/train.csv', transform=transforms.ToTensor())","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:06:24.035895Z","iopub.execute_input":"2024-01-12T14:06:24.036352Z","iopub.status.idle":"2024-01-12T14:06:29.396106Z","shell.execute_reply.started":"2024-01-12T14:06:24.036310Z","shell.execute_reply":"2024-01-12T14:06:29.395123Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data = TestMNIST('/kaggle/input/Kannada-MNIST/test.csv', transform=transforms.ToTensor())","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:06:31.564265Z","iopub.execute_input":"2024-01-12T14:06:31.564713Z","iopub.status.idle":"2024-01-12T14:06:31.968910Z","shell.execute_reply.started":"2024-01-12T14:06:31.564681Z","shell.execute_reply":"2024-01-12T14:06:31.967751Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-01-12T14:06:34.018189Z","iopub.execute_input":"2024-01-12T14:06:34.018616Z","iopub.status.idle":"2024-01-12T14:06:34.025260Z","shell.execute_reply.started":"2024-01-12T14:06:34.018578Z","shell.execute_reply":"2024-01-12T14:06:34.024119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n%matplotlib inline\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, axes = plt.subplots(nrows=2, ncols=10, figsize=(25, 4))\n\nfor idx, ax in enumerate(axes.flatten()):\n    ax.imshow(np.squeeze(images[idx]), cmap='gray')\n    ax.set_xticks([])\n    ax.set_yticks([])\n    ax.set_title(str(labels[idx].item()))\n\nplt.tight_layout()\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:06:36.450996Z","iopub.execute_input":"2024-01-12T14:06:36.451393Z","iopub.status.idle":"2024-01-12T14:06:37.954295Z","shell.execute_reply.started":"2024-01-12T14:06:36.451363Z","shell.execute_reply":"2024-01-12T14:06:37.953352Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"---\n### 4. Thiết kế 1 mạng NN đơn giản [Architecture](http://pytorch.org/docs/stable/nn.html)\n\nThiết kế 1 mạng neural network đơn giản cho việc phân loại","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\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":{"execution":{"iopub.status.busy":"2024-01-12T14:06:41.170949Z","iopub.execute_input":"2024-01-12T14:06:41.171327Z","iopub.status.idle":"2024-01-12T14:06:41.193109Z","shell.execute_reply.started":"2024-01-12T14:06:41.171298Z","shell.execute_reply":"2024-01-12T14:06:41.191935Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"###  5. Chọn [Loss Function](http://pytorch.org/docs/stable/nn.html#loss-functions) và [Optimizer](http://pytorch.org/docs/stable/optim.html)","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":{"execution":{"iopub.status.busy":"2024-01-12T14:06:45.114904Z","iopub.execute_input":"2024-01-12T14:06:45.115339Z","iopub.status.idle":"2024-01-12T14:06:45.121086Z","shell.execute_reply.started":"2024-01-12T14:06:45.115306Z","shell.execute_reply":"2024-01-12T14:06:45.119832Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"---\n### 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":{"execution":{"iopub.status.busy":"2024-01-12T14:14:22.636319Z","iopub.execute_input":"2024-01-12T14:14:22.637530Z","iopub.status.idle":"2024-01-12T14:21:29.766145Z","shell.execute_reply.started":"2024-01-12T14:14:22.637493Z","shell.execute_reply":"2024-01-12T14:21:29.765143Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-01-12T14:24:06.117541Z","iopub.execute_input":"2024-01-12T14:24:06.118008Z","iopub.status.idle":"2024-01-12T14:24:06.129522Z","shell.execute_reply.started":"2024-01-12T14:24:06.117974Z","shell.execute_reply":"2024-01-12T14:24:06.128356Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"---\n## Test the Trained Network\n\nFinally, we test our best model on previously unseen **test data** and evaluate it's performance. Testing on unseen data is a good way to check that our model generalizes well. It may also be useful to be granular in this analysis and take a look at how this model performs on each class as well as looking at its overall loss and accuracy.","metadata":{}},{"cell_type":"markdown","source":"### Visualize Sample Test Results\n\nThis cell displays test images and their labels in this format: `predicted (ground-truth)`. The text will be green for accurately classified examples and red for incorrect predictions.","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 range(20):\n    ax = fig.add_subplot(2, 10, 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":"2024-01-12T14:24:08.960660Z","iopub.execute_input":"2024-01-12T14:24:08.961098Z","iopub.status.idle":"2024-01-12T14:24:10.095209Z","shell.execute_reply.started":"2024-01-12T14:24:08.961061Z","shell.execute_reply":"2024-01-12T14:24:10.094077Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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,\n    num_workers=num_workers)\n","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:24:13.914500Z","iopub.execute_input":"2024-01-12T14:24:13.914902Z","iopub.status.idle":"2024-01-12T14:24:13.921678Z","shell.execute_reply.started":"2024-01-12T14:24:13.914868Z","shell.execute_reply":"2024-01-12T14:24:13.919171Z"},"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":"2024-01-12T14:24:17.466142Z","iopub.execute_input":"2024-01-12T14:24:17.466867Z","iopub.status.idle":"2024-01-12T14:24:17.472566Z","shell.execute_reply.started":"2024-01-12T14:24:17.466833Z","shell.execute_reply":"2024-01-12T14:24:17.471760Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = predict(model,test_loader)","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:36:13.642660Z","iopub.execute_input":"2024-01-12T14:36:13.644030Z","iopub.status.idle":"2024-01-12T14:36:16.409763Z","shell.execute_reply.started":"2024-01-12T14:36:13.643985Z","shell.execute_reply":"2024-01-12T14:36:16.408349Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"flattened_predictions = [item for sublist in predictions for item in sublist]\npredictions_array = np.array(flattened_predictions)","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:36:19.162768Z","iopub.execute_input":"2024-01-12T14:36:19.163228Z","iopub.status.idle":"2024-01-12T14:36:19.229920Z","shell.execute_reply.started":"2024-01-12T14:36:19.163190Z","shell.execute_reply":"2024-01-12T14:36:19.228893Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions_array","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:36:21.858090Z","iopub.execute_input":"2024-01-12T14:36:21.858481Z","iopub.status.idle":"2024-01-12T14:36:21.865539Z","shell.execute_reply.started":"2024-01-12T14:36:21.858450Z","shell.execute_reply":"2024-01-12T14:36:21.864410Z"},"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\": predictions_array\n})\n","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:36:25.140134Z","iopub.execute_input":"2024-01-12T14:36:25.140556Z","iopub.status.idle":"2024-01-12T14:36:25.465677Z","shell.execute_reply.started":"2024-01-12T14:36:25.140523Z","shell.execute_reply":"2024-01-12T14:36:25.464566Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:36:28.060763Z","iopub.execute_input":"2024-01-12T14:36:28.061305Z","iopub.status.idle":"2024-01-12T14:36:28.077047Z","shell.execute_reply.started":"2024-01-12T14:36:28.061260Z","shell.execute_reply":"2024-01-12T14:36:28.075658Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2024-01-12T14:25:22.298387Z","iopub.execute_input":"2024-01-12T14:25:22.298753Z","iopub.status.idle":"2024-01-12T14:25:22.313972Z","shell.execute_reply.started":"2024-01-12T14:25:22.298724Z","shell.execute_reply":"2024-01-12T14:25:22.313089Z"},"trusted":true},"execution_count":null,"outputs":[]}]}