{"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":"markdown","source":"# 1. Import libraries","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"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":{"execution":{"iopub.status.busy":"2024-01-12T15:51:00.952658Z","iopub.execute_input":"2024-01-12T15:51:00.953213Z","iopub.status.idle":"2024-01-12T15:51:03.592236Z","shell.execute_reply.started":"2024-01-12T15:51:00.953166Z","shell.execute_reply":"2024-01-12T15:51:03.591102Z"},"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        #load image as ndarray type (Height * Width * Channels)\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\n\nclass 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        #load image as ndarray type (Height * Width * Channels)\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":"2024-01-12T15:51:03.593981Z","iopub.execute_input":"2024-01-12T15:51:03.594510Z","iopub.status.idle":"2024-01-12T15:51:03.606293Z","shell.execute_reply.started":"2024-01-12T15:51:03.594476Z","shell.execute_reply":"2024-01-12T15:51:03.605263Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-01-12T15:51:03.607473Z","iopub.execute_input":"2024-01-12T15:51:03.608513Z","iopub.status.idle":"2024-01-12T15:51:10.264094Z","shell.execute_reply.started":"2024-01-12T15:51:03.608466Z","shell.execute_reply":"2024-01-12T15:51:10.262979Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Count samples\nnum_train_samples = len(train_data)\nnum_test_samples = len(test_data)\nprint('Number of samples in trainset:  ',num_train_samples)\nprint('Number of samples in trainset:  ',num_test_samples)","metadata":{"execution":{"iopub.status.busy":"2024-01-12T15:51:10.266771Z","iopub.execute_input":"2024-01-12T15:51:10.267119Z","iopub.status.idle":"2024-01-12T15:51:10.275086Z","shell.execute_reply.started":"2024-01-12T15:51:10.267089Z","shell.execute_reply":"2024-01-12T15:51:10.273799Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_workers = 0\nbatch_size = 20\n\ntrain_loader = torch.utils.data.DataLoader(train_data, batch_size = batch_size, \n                                           num_workers = num_workers)\n# test_loader = torch.utils.data.DataLoader(test_data, batch_size = batch_size,\n#                                          num_workers = num_workers)  \n# test_loader này chỉ để dùng visualize test.csv nếu muốn, chứ không dùng để predict. Predict thì batch_size=1.","metadata":{"execution":{"iopub.status.busy":"2024-01-12T15:51:10.276734Z","iopub.execute_input":"2024-01-12T15:51:10.277171Z","iopub.status.idle":"2024-01-12T15:51:10.287211Z","shell.execute_reply.started":"2024-01-12T15:51:10.277131Z","shell.execute_reply":"2024-01-12T15:51:10.286185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Visualize train.csv\nimport 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    ax.set_title(str(labels[idx].item()))","metadata":{"execution":{"iopub.status.busy":"2024-01-12T15:51:10.288540Z","iopub.execute_input":"2024-01-12T15:51:10.288937Z","iopub.status.idle":"2024-01-12T15:51:11.649861Z","shell.execute_reply.started":"2024-01-12T15:51:10.288906Z","shell.execute_reply":"2024-01-12T15:51:11.648938Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 4. Build a simple Neural Network","metadata":{}},{"cell_type":"code","source":"import torch.nn as nn\nimport torch.nn.functional as F\n\nclass Net(nn.Module):\n    def __init__(self):\n        super(Net, self).__init__()\n        hidden_1 = 512\n        hidden_2 = 512\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        #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        x = F.relu(self.fc2(x))\n        x = self.fc3(x)\n        return x\n    \nmodel = Net()\nprint(model)","metadata":{"execution":{"iopub.status.busy":"2024-01-12T15:51:11.651275Z","iopub.execute_input":"2024-01-12T15:51:11.652457Z","iopub.status.idle":"2024-01-12T15:51:11.674052Z","shell.execute_reply.started":"2024-01-12T15:51:11.652406Z","shell.execute_reply":"2024-01-12T15:51:11.672854Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 5. Loss Function and Optimizer","metadata":{}},{"cell_type":"code","source":"criterion = nn.CrossEntropyLoss()\noptimizer = torch.optim.SGD(model.parameters(), lr=0.01)","metadata":{"execution":{"iopub.status.busy":"2024-01-12T15:51:11.675390Z","iopub.execute_input":"2024-01-12T15:51:11.676087Z","iopub.status.idle":"2024-01-12T15:51:11.681537Z","shell.execute_reply.started":"2024-01-12T15:51:11.676055Z","shell.execute_reply":"2024-01-12T15:51:11.680473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 6. Train the network","metadata":{}},{"cell_type":"code","source":"n_epochs = 40\ntrain_loss_min = np.Inf\n\nfor epoch in range(n_epochs):\n    train_loss = 0.0\n    model.train()\n    for data, target in train_loader:\n        optimizer.zero_grad()   # clear the gradients of all optimized variables\n        output = model(data)\n        loss = criterion(output, target)\n        loss.backward()\n        optimizer.step()   # perform a single optimization step (parameter update)\n        train_loss += loss.item()*data.size(0)\n        \n    train_loss = train_loss/len(train_loader.dataset)\n    print('Epoch: {} \\t Training loss {:.6f}'.format(epoch+1, train_loss))\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(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":"2024-01-12T15:51:11.683192Z","iopub.execute_input":"2024-01-12T15:51:11.683824Z","iopub.status.idle":"2024-01-12T16:04:39.629549Z","shell.execute_reply.started":"2024-01-12T15:51:11.683788Z","shell.execute_reply":"2024-01-12T16:04:39.628673Z"},"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":"2024-01-12T16:04:39.632741Z","iopub.execute_input":"2024-01-12T16:04:39.633422Z","iopub.status.idle":"2024-01-12T16:04:39.644326Z","shell.execute_reply.started":"2024-01-12T16:04:39.633390Z","shell.execute_reply":"2024-01-12T16:04:39.643238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Visualize test.csv\n# dataiter = iter(test_loader)\n# images = next(dataiter)\n\n# output = model(images)\n# # convert output probabilities to predicted class\n# _, preds = torch.max(output, 1)\n# images = images.numpy()\n\n# fig = plt.figure(figsize = (25,4))\n# for 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":"2024-01-12T16:04:39.646028Z","iopub.execute_input":"2024-01-12T16:04:39.646388Z","iopub.status.idle":"2024-01-12T16:04:39.654685Z","shell.execute_reply.started":"2024-01-12T16:04:39.646360Z","shell.execute_reply":"2024-01-12T16:04:39.653475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 7. Predict Kannada digit based on input","metadata":{}},{"cell_type":"code","source":"test_loader = torch.utils.data.DataLoader(test_data, batch_size=1,num_workers=num_workers)\n\n\ndef 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\n\n\npredictions = predict(model,test_loader)\n# predictions = np.array(predictions)  # error: The requested array has an inhomogeneous shape after 1 dimensions.\noutput = []\nfor i in predictions:\n    output.append(i.item())\noutput = np.array(output)","metadata":{"execution":{"iopub.status.busy":"2024-01-12T16:04:39.656341Z","iopub.execute_input":"2024-01-12T16:04:39.656729Z","iopub.status.idle":"2024-01-12T16:04:42.624633Z","shell.execute_reply.started":"2024-01-12T16:04:39.656698Z","shell.execute_reply":"2024-01-12T16:04:42.623628Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 8. Create file submission on kaggle","metadata":{}},{"cell_type":"code","source":"test_df = pd.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\")\n\nsubmission = pd.DataFrame(data={\n    \"id\": test_df['id'],\n    \"label\": output\n})\nsubmission.to_csv(\"submission.csv\", index=None)","metadata":{"execution":{"iopub.status.busy":"2024-01-12T16:04:42.626154Z","iopub.execute_input":"2024-01-12T16:04:42.626525Z","iopub.status.idle":"2024-01-12T16:04:43.045203Z","shell.execute_reply.started":"2024-01-12T16:04:42.626494Z","shell.execute_reply":"2024-01-12T16:04:43.043992Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"execution":{"iopub.status.busy":"2024-01-12T16:04:43.046645Z","iopub.execute_input":"2024-01-12T16:04:43.047084Z","iopub.status.idle":"2024-01-12T16:04:43.064710Z","shell.execute_reply.started":"2024-01-12T16:04:43.047050Z","shell.execute_reply":"2024-01-12T16:04:43.063483Z"},"trusted":true},"execution_count":null,"outputs":[]}]}