{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2220571ed4fe04871f9c223384a951e77c28e958"},"cell_type":"code","source":"# Import Libraries\nimport 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":{"trusted":true,"_uuid":"d21152ba299417df5bdadd4758b2fae64a7c7b4d"},"cell_type":"code","source":"# Prepare Dataset\n# load data\ntrain = pd.read_csv(r\"../input/train.csv\",dtype = np.float32)\n\n# split data into features(pixels) and labels(numbers from 0 to 9)\ntargets_numpy = train.label.values\nfeatures_numpy = 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%. \nfeatures_train, features_test, targets_train, targets_test = train_test_split(features_numpy,\n                                                                             targets_numpy,\n                                                                             test_size = 0.2,\n                                                                             random_state = 42) \n\n# create feature and targets tensor for train set. We need variable to accumulate gradients. Therefore first we create tensor, then we will create variable\nfeaturesTrain = torch.from_numpy(features_train)\ntargetsTrain = torch.from_numpy(targets_train).type(torch.LongTensor) # data type is long\n\n# create feature and targets tensor for test set.\nfeaturesTest = torch.from_numpy(features_test)\ntargetsTest = torch.from_numpy(targets_test).type(torch.LongTensor) # data type is long\n\n# batch_size, epoch and iteration\nbatch_size = 100\nn_iters = 2500\nnum_epochs = n_iters / (len(features_train) / batch_size)\nnum_epochs = int(num_epochs)\n\n# Pytorch train and test sets\ntrain = torch.utils.data.TensorDataset(featuresTrain,targetsTrain)\ntest = torch.utils.data.TensorDataset(featuresTest,targetsTest)\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)","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"# Create CNN Model\nclass Netz(nn.Module):\n    def __init__(self):\n        super(Netz, self).__init__()\n        self.conv1 = 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.conv2 = 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, 80)\n        self.relu3 = nn.ReLU()\n        self.fc2 = nn.Linear(80, 10)\n    \n    def forward(self, x):\n        out = self.conv1(x)\n        out = self.relu1(out)\n        out = self.maxpool1(out)\n        out = self.conv2(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        out = self.relu3(out)\n        out = self.fc2(out)\n        return out\n    \n# Create CNN\nmodel = Netz()\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,"_uuid":"0e1b5c84b2b7bcb6b13016d778c49ee312908af5"},"cell_type":"code","source":"# CNN model training\ncount = 0\nloss_list = []\niteration_list = []\naccuracy_list = []\nfor epoch in range(num_epochs):\n    for i, (images, labels) in enumerate(train_loader):\n        \n        train = Variable(images.view(100,1,28,28))\n        labels = Variable(labels)\n        \n        # Clear gradients\n        optimizer.zero_grad()\n        \n        # Forward propagation\n        outputs = model(train)\n        \n        # Calculate softmax and cross entropy loss\n        loss = error(outputs, labels)\n        \n        # Calculating gradients\n        loss.backward()\n        \n        # Update parameters\n        optimizer.step()\n        count += 1\n        if count % 50 == 0:\n            # Calculate Accuracy         \n            correct = 0\n            total = 0\n            # Iterate through test dataset\n            for images, labels in test_loader:\n                \n                test = Variable(images.view(100,1,28,28))\n                \n                # Forward propagation\n                outputs = model(test)\n                \n                # Get predictions from the maximum value\n                predicted = torch.max(outputs.data, 1)[1]\n                \n                # Total number of labels\n                total += len(labels)\n                \n                correct += (predicted == labels).sum()\n            \n            accuracy = 100.0 * float(correct) / float(total)\n            \n            # store loss and iteration\n            loss_list.append(loss.data)\n            iteration_list.append(count)\n            accuracy_list.append(accuracy)\n            if count % 200 == 0:\n                # Print Loss\n                print('Iteration: {}  Loss: {}  Accuracy: {} %'.format(count, loss.item(), accuracy))","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}