{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.13","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":30733,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import torch\nfrom torch.utils.data import DataLoader,Dataset\nimport torch.nn as nn\nimport torchvision\nimport torchvision.transforms as transforms\nfrom torch.utils.data.sampler import SubsetRandomSampler\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:05:12.733109Z","iopub.execute_input":"2024-07-05T17:05:12.733396Z","iopub.status.idle":"2024-07-05T17:05:15.890243Z","shell.execute_reply.started":"2024-07-05T17:05:12.733366Z","shell.execute_reply":"2024-07-05T17:05:15.889432Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## STEP 1: Init dataset and dataloader","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, idx):\n        img = self.data.iloc[idx,1:].values.astype(np.uint8).reshape((28, 28, 1))\n        label = self.data.iloc[idx,0]\n        if self.transform is not None:\n            img = self.transform(img)\n        return img,label","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:05:15.894943Z","iopub.execute_input":"2024-07-05T17:05:15.895218Z","iopub.status.idle":"2024-07-05T17:05:15.902016Z","shell.execute_reply.started":"2024-07-05T17:05:15.895187Z","shell.execute_reply":"2024-07-05T17:05:15.901083Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class 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, idx):\n        img = self.data.iloc[idx,1:].values.astype(np.uint8).reshape((28, 28, 1))\n        \n        if self.transform is not None:\n            img = self.transform(img)\n        return img","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:05:15.903118Z","iopub.execute_input":"2024-07-05T17:05:15.903386Z","iopub.status.idle":"2024-07-05T17:05:15.913951Z","shell.execute_reply.started":"2024-07-05T17:05:15.903363Z","shell.execute_reply":"2024-07-05T17:05:15.912988Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-07-05T17:05:15.917518Z","iopub.execute_input":"2024-07-05T17:05:15.917977Z","iopub.status.idle":"2024-07-05T17:05:19.964759Z","shell.execute_reply.started":"2024-07-05T17:05:15.917952Z","shell.execute_reply":"2024-07-05T17:05:19.963917Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_workers = 0\nbatch_size = 20\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":"2024-07-05T17:05:19.965758Z","iopub.execute_input":"2024-07-05T17:05:19.966021Z","iopub.status.idle":"2024-07-05T17:05:19.971356Z","shell.execute_reply.started":"2024-07-05T17:05:19.965998Z","shell.execute_reply":"2024-07-05T17:05:19.970476Z"},"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\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() gets the value contained in a Tensor\n    ax.set_title(str(labels[idx].item()))","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:05:19.972468Z","iopub.execute_input":"2024-07-05T17:05:19.972858Z","iopub.status.idle":"2024-07-05T17:05:21.020473Z","shell.execute_reply.started":"2024-07-05T17:05:19.972807Z","shell.execute_reply":"2024-07-05T17:05:21.019524Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# STEP 2: Define the model","metadata":{}},{"cell_type":"code","source":"fc1 = nn.Linear(28*28, 12)","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:05:21.021887Z","iopub.execute_input":"2024-07-05T17:05:21.022342Z","iopub.status.idle":"2024-07-05T17:05:21.027999Z","shell.execute_reply.started":"2024-07-05T17:05:21.022309Z","shell.execute_reply":"2024-07-05T17:05:21.027102Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch.nn.functional as F\n\n\nclass Net(nn.Module):\n    def __init__(self):\n        super(Net, self).__init__()\n        hidden_1 = 512\n        hidden_2 = 512\n        hidden_3=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, hidden_3)\n        self.fc4 = nn.Linear(hidden_3, 10)\n    def forward(self,x):\n        x = x.flatten(start_dim=1)\n        x = F.tanh(self.fc1(x))\n        x = F.tanh(self.fc2(x))\n        x = F.tanh(self.fc3(x))\n        x = self.fc4(x)\n        return x\ndevice = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\nmodel=Net()\nmodel.to(device)\nprint(model)","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:05:21.029163Z","iopub.execute_input":"2024-07-05T17:05:21.029530Z","iopub.status.idle":"2024-07-05T17:05:21.169352Z","shell.execute_reply.started":"2024-07-05T17:05:21.029498Z","shell.execute_reply":"2024-07-05T17:05:21.168401Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# STEP 3: Define the loss function and optimizer","metadata":{}},{"cell_type":"code","source":"loss=nn.CrossEntropyLoss() #cross entropy loss for classification\noptimizer=torch.optim.Adam(model.parameters(),lr=0.001) #Adamtive optimizer","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:05:21.170693Z","iopub.execute_input":"2024-07-05T17:05:21.170994Z","iopub.status.idle":"2024-07-05T17:05:21.176057Z","shell.execute_reply.started":"2024-07-05T17:05:21.170968Z","shell.execute_reply":"2024-07-05T17:05:21.175141Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# STEP 4: Train the model","metadata":{}},{"cell_type":"code","source":"n_epochs = 20\ntrain_loss_min = np.Inf\n\n\n\nfor epoch in range(n_epochs):\n    train_loss = 0.0\n    model.train()\n    for data, target in train_loader:\n        data, target = data.to(device), target.to(device)\n        optimizer.zero_grad()  # clear the gradients of all optimized variable\n        output = model(data)\n        loss_output = loss(output, target)\n        loss_output.backward() #Derivative\n        optimizer.step() #Update weights\n        train_loss += loss_output.item()*data.size(0)\n        mean_loss = train_loss/len(train_loader.dataset)\n\n    print(f'Epoch: {epoch} \\tTraining Loss: {mean_loss:.6f}')\n    if mean_loss <= train_loss_min:\n        print('Loss decreased ({:.6f} --> {:.6f}).  Saving model ...'.format(train_loss_min,mean_loss))\n        torch.save(model.state_dict(), 'model.pt') #Save model\n        train_loss_min = mean_loss","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:05:21.177408Z","iopub.execute_input":"2024-07-05T17:05:21.177731Z","iopub.status.idle":"2024-07-05T17:10:47.588451Z","shell.execute_reply.started":"2024-07-05T17:05:21.177704Z","shell.execute_reply":"2024-07-05T17:10:47.587544Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.load_state_dict(torch.load('model.pt'))","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:10:47.589867Z","iopub.execute_input":"2024-07-05T17:10:47.590223Z","iopub.status.idle":"2024-07-05T17:10:47.602729Z","shell.execute_reply.started":"2024-07-05T17:10:47.590188Z","shell.execute_reply":"2024-07-05T17:10:47.601573Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Test the model","metadata":{}},{"cell_type":"code","source":"dataiter=iter(test_loader)\nimages=next(dataiter)\noutput=model(images.to(device))\n_, preds = torch.max(output, 1)\nimages = images.numpy()\nfig = plt.figure(figsize=(25, 4))\nfor idx in range(test_loader.batch_size):\n    ax = fig.add_subplot(2, int(test_loader.batch_size/2), idx+1, xticks=[], yticks=[])\n    ax.imshow(np.squeeze(images[idx]), cmap='gray')\n    ax.set_title(str(preds[idx].item()), color=(\"green\" ))","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:10:47.604003Z","iopub.execute_input":"2024-07-05T17:10:47.604644Z","iopub.status.idle":"2024-07-05T17:10:48.575874Z","shell.execute_reply.started":"2024-07-05T17:10:47.604610Z","shell.execute_reply":"2024-07-05T17:10:48.574950Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Predict Test Data and Submit","metadata":{}},{"cell_type":"code","source":"def predict(data,dataloader):\n    rs=[]\n    for idx,batch in enumerate(dataloader):\n        output=model(batch.to(device))\n        _, preds = torch.max(output, 1)\n        rs.append(preds.cpu().numpy())\n    return rs","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:10:48.580124Z","iopub.execute_input":"2024-07-05T17:10:48.580609Z","iopub.status.idle":"2024-07-05T17:10:48.586237Z","shell.execute_reply.started":"2024-07-05T17:10:48.580554Z","shell.execute_reply":"2024-07-05T17:10:48.585377Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"new_batch=1\ntest_loader = torch.utils.data.DataLoader(test_data, batch_size=new_batch, \n    num_workers=num_workers)\nrs=predict(test_data,test_loader)\n","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:10:48.587406Z","iopub.execute_input":"2024-07-05T17:10:48.587752Z","iopub.status.idle":"2024-07-05T17:10:51.659980Z","shell.execute_reply.started":"2024-07-05T17:10:48.587721Z","shell.execute_reply":"2024-07-05T17:10:51.658906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission=pd.DataFrame(data={\n    'id':np.arange(len(rs)),\n    'label':np.concatenate(rs)\n})","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:10:51.661280Z","iopub.execute_input":"2024-07-05T17:10:51.661636Z","iopub.status.idle":"2024-07-05T17:10:51.669921Z","shell.execute_reply.started":"2024-07-05T17:10:51.661580Z","shell.execute_reply":"2024-07-05T17:10:51.668893Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv('submission.csv',index=False)","metadata":{"execution":{"iopub.status.busy":"2024-07-05T17:10:51.671063Z","iopub.execute_input":"2024-07-05T17:10:51.671388Z","iopub.status.idle":"2024-07-05T17:10:51.687758Z","shell.execute_reply.started":"2024-07-05T17:10:51.671362Z","shell.execute_reply":"2024-07-05T17:10:51.686656Z"},"trusted":true},"execution_count":null,"outputs":[]}]}