{"cells":[{"metadata":{},"cell_type":"markdown","source":"## Pytorch : 1. ANN & Simple CNN\n\n> This Kernel is based on [Pytorch Tutorial for Deep Learning Lovers](https://www.kaggle.com/kanncaa1/pytorch-tutorial-for-deep-learning-lovers)\n\nThe project following the visualization is a deep learning model implementation project. Many people use the framework, but it is difficult to implement the paper. Through this project, I would like to develop the ability to implement papers.\n\n- ANN\n- Simple CNN\n"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport torchvision.transforms as transforms\nfrom torch.autograd import Variable\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd \nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/Kannada-MNIST/train.csv\",dtype = np.float32)\n\n# split data into features(pixels) and labels(numbers from 0 to 9)\ntarget = train.label.values\ntrain = train.loc[:,train.columns != \"label\"].values/255 # normalization\n\n# train test split. Size of train data is 80% and size of test data is 20%. \nX_train, X_test, y_train, y_test = train_test_split(train, target, test_size = 0.2, random_state = 42) \n\n# create feature and targets tensor for train set. As you remember we need variable to accumulate gradients. Therefore first we create tensor, then we will create variable\nX_train = torch.from_numpy(X_train)\ny_train = torch.from_numpy(y_train).type(torch.LongTensor) # data type is long\n\n# create feature and targets tensor for test set.\nX_test = torch.from_numpy(X_test)\ny_test = torch.from_numpy(y_test).type(torch.LongTensor) # data type is long\n\n# batch_size, epoch and iteration\nbatch_size = 100\nn_iters = 10000\nnum_epochs = n_iters / (len(X_train) / batch_size)\nnum_epochs = int(num_epochs)\n\n# Pytorch train and test sets\ntrain = torch.utils.data.TensorDataset(X_train, y_train)\ntest = torch.utils.data.TensorDataset(X_test, y_test)\n\n# data loader\ntrain_loader = torch.utils.data.DataLoader(train, batch_size = batch_size, shuffle = False)\ntest_loader = torch.utils.data.DataLoader(test, batch_size = batch_size, shuffle = False)\n\n# visualize one of the images in data set\nplt.imshow(X_train[10].reshape(28,28))\nplt.axis(\"off\")\nplt.title(str(y_train[10]))\nplt.savefig('graph.png')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## ANN (Artificial Neural Network)"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Import Libraries\nimport torch\nimport torch.nn as nn\nimport torchvision.transforms as transforms\nfrom torch.autograd import Variable","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Create ANN Model\nclass ANNModel(nn.Module):\n    def __init__(self, input_dim, hidden_dim, output_dim):\n        super(ANNModel, self).__init__()\n        # Linear function 1: 784 --> 100\n        self.fc1 = nn.Linear(input_dim, hidden_dim) \n        self.relu1 = nn.ReLU()\n        self.fc2 = nn.Linear(hidden_dim, hidden_dim)\n        self.relu2 = nn.ReLU()\n        self.fc3 = nn.Linear(hidden_dim, hidden_dim)\n        self.relu3 = nn.ReLU()\n        self.fc4 = nn.Linear(hidden_dim, output_dim)  \n    \n    def forward(self, x):\n        out = self.fc1(x)\n        out = self.relu1(out)\n        out = self.fc2(out)\n        out = self.relu2(out)\n        out = self.fc3(out)\n        out = self.relu3(out)\n        out = self.fc4(out)\n        return out\n\n# instantiate ANN\ninput_dim = 28*28\n\nhidden_dim = 100 \noutput_dim = 10\n\n# Create ANN\nmodel = ANNModel(input_dim, hidden_dim, output_dim)\n\n# Cross Entropy Loss \nerror = nn.CrossEntropyLoss()\n\n# SGD Optimizer\nlearning_rate = 0.02\noptimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# ANN model training\ncount = 0\nloss_list = []\niteration_list = []\naccuracy_list = []\n\nfor epoch in range(num_epochs):\n    for i, (images, labels) in enumerate(train_loader):\n\n        train = Variable(images.view(-1, 28*28))\n        labels = Variable(labels)\n        \n        \n        optimizer.zero_grad() # Clear gradients\n        outputs = model(train) # Forward propagation\n        loss = error(outputs, labels) # Calculate softmax and cross entropy loss\n        loss.backward() # Calculating gradients\n        optimizer.step() # Update parameters\n        \n        count += 1\n        \n        if count % 50 == 0:\n            # Calculate Accuracy         \n            correct = 0\n            total = 0\n            \n            # Predict test dataset\n            for images, labels in test_loader:\n                test = Variable(images.view(-1, 28*28))\n                outputs = model(test) # Forward propagation\n                predicted = torch.max(outputs.data, 1)[1] # Get predictions from the maximum value\n                total += len(labels) # Total number of labels\n                correct += (predicted == labels).sum() # Total correct predictions\n            \n            accuracy = 100.0 * correct.item() / total\n            \n            # store loss and iteration\n            loss_list.append(loss.data.item())\n            iteration_list.append(count)\n            accuracy_list.append(accuracy)\n            if count % 500 == 0:\n                print('Iteration: {}  Loss: {}  Accuracy: {} %'.format(count, loss.data.item(), accuracy))\n                ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# visualization loss \n\nplt.plot(iteration_list,loss_list)\nplt.xlabel(\"Number of iteration\")\nplt.ylabel(\"Loss\")\nplt.title(\"ANN: Loss vs Number of iteration\")\nplt.show()\n\n# visualization accuracy \nplt.plot(iteration_list,accuracy_list,color = \"red\")\nplt.xlabel(\"Number of iteration\")\nplt.ylabel(\"Accuracy\")\nplt.title(\"ANN: Accuracy vs Number of iteration\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## CNN (Convolution Neural Network)"},{"metadata":{"trusted":true},"cell_type":"code","source":"class CNNModel(nn.Module):\n    def __init__(self):\n        super(CNNModel, self).__init__()\n        self.cnn1 = nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=0)\n        self.relu1 = nn.ReLU()\n        self.maxpool1 = nn.MaxPool2d(kernel_size=2)\n        self.cnn2 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5, stride=1, padding=0)\n        self.relu2 = nn.ReLU()\n        self.maxpool2 = nn.MaxPool2d(kernel_size=2)\n        self.fc1 = nn.Linear(32 * 4 * 4, 10) \n    \n    def forward(self, x):\n        out = self.cnn1(x)\n        out = self.relu1(out)\n        out = self.maxpool1(out)\n        out = self.cnn2(out)\n        out = self.relu2(out)\n        out = self.maxpool2(out)\n        out = out.view(out.size(0), -1)\n        out = self.fc1(out)\n        return out","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Create CNN\nmodel = CNNModel()\n\n# Cross Entropy Loss \nerror = nn.CrossEntropyLoss()\n\n# SGD Optimizer\nlearning_rate = 0.1\noptimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# CNN model training\ncount = 0\nloss_list = []\niteration_list = []\naccuracy_list = []\n\nfor epoch in range(num_epochs):\n    for i, (images, labels) in enumerate(train_loader):\n\n        train = Variable(images.view(-1, 1, 28, 28))\n        labels = Variable(labels)\n        \n        \n        optimizer.zero_grad() # Clear gradients\n        outputs = model(train) # Forward propagation\n        loss = error(outputs, labels) # Calculate softmax and cross entropy loss\n        loss.backward() # Calculating gradients\n        optimizer.step() # Update parameters\n        \n        count += 1\n        \n        if count % 50 == 0:\n            # Calculate Accuracy         \n            correct = 0\n            total = 0\n            \n            # Predict test dataset\n            for images, labels in test_loader:\n                test = Variable(images.view(-1, 1, 28, 28))\n                outputs = model(test) # Forward propagation\n                predicted = torch.max(outputs.data, 1)[1] # Get predictions from the maximum value\n                total += len(labels) # Total number of labels\n                correct += (predicted == labels).sum() # Total correct predictions\n            \n            accuracy = 100.0 * correct.item() / total\n            \n            # store loss and iteration\n            loss_list.append(loss.data.item())\n            iteration_list.append(count)\n            accuracy_list.append(accuracy)\n            if count % 500 == 0:\n                print('Iteration: {}  Loss: {}  Accuracy: {} %'.format(count, loss.data.item(), accuracy))\n                ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# visualization loss \nplt.plot(iteration_list,loss_list)\nplt.xlabel(\"Number of iteration\")\nplt.ylabel(\"Loss\")\nplt.title(\"CNN: Loss vs Number of iteration\")\nplt.show()\n\n# visualization accuracy \nplt.plot(iteration_list,accuracy_list,color = \"red\")\nplt.xlabel(\"Number of iteration\")\nplt.ylabel(\"Accuracy\")\nplt.title(\"CNN: Accuracy vs Number of iteration\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Submit"},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv(\"../input/Kannada-MNIST/test.csv\",dtype = np.float32)\n\nindex = test['id']\ntest.drop('id', axis=1, inplace=True)\ntest = test.values/255 # normalization\n\ntest = torch.from_numpy(test)\ntest = Variable(test.view(-1, 1, 28, 28))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"res = model(test)\nsub = pd.read_csv(\"../input/Kannada-MNIST/sample_submission.csv\")\nsub['label'] = torch.max(res.data, 1)[1]\nsub.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":1}