{"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\n\nfrom __future__ import print_function, division\n\n\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torch.optim import lr_scheduler\nimport torchvision\nfrom torchvision import datasets, models, transforms\nimport matplotlib.pyplot as plt\nimport time\nimport os\nimport copy\n\n\nplt.ion()   # interactive mode\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\nimport torch\n%matplotlib inline\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},"cell_type":"code","source":"train_dir = '../input/train'\ntest_dir = '../input/test1'\ndata_dir = '../input'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def imshow(image, ax=None, title=None, normalize=True):\n    \"\"\"Imshow for Tensor.\"\"\"\n    if ax is None:\n        fig, ax = plt.subplots()\n    image = image.numpy().transpose((1, 2, 0))\n\n    if normalize:\n        mean = np.array([0.485, 0.456, 0.406])\n        std = np.array([0.229, 0.224, 0.225])\n        image = std * image + mean\n        image = np.clip(image, 0, 1)\n\n    ax.imshow(image)\n    ax.spines['top'].set_visible(False)\n    ax.spines['right'].set_visible(False)\n    ax.spines['left'].set_visible(False)\n    ax.spines['bottom'].set_visible(False)\n    ax.tick_params(axis='both', length=0)\n    ax.set_xticklabels('')\n    ax.set_yticklabels('')\n\n    return ax","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"transform = transforms.Compose([transforms.Resize(255),\n                                transforms.CenterCrop(224),\n                                transforms.ToTensor()])\ndataset = datasets.ImageFolder(train_dir, transform=transform)\ndataloader = torch.utils.data.DataLoader(dataset, batch_size=32, shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#testing the data loader\nimages, labels = next(iter(dataloader))\nimshow(images[0], normalize=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_dir = '../input'\n\ntrain_transforms = transforms.Compose([transforms.RandomRotation(30),\n                                       transforms.RandomResizedCrop(224),\n                                       transforms.RandomHorizontalFlip(),\n                                       transforms.ToTensor(),\n                                       transforms.Normalize([0.485, 0.456, 0.406],\n                                                            [0.229, 0.224, 0.225])])\n\ntest_transforms = transforms.Compose([transforms.Resize(255),\n                                      transforms.CenterCrop(224),\n                                      transforms.ToTensor(),\n                                      transforms.Normalize([0.485, 0.456, 0.406],\n                                                           [0.229, 0.224, 0.225])])\n\n# Pass transforms in here, then run the next cell to see how the transforms look\ntrain_data = datasets.ImageFolder(data_dir + '/train', transform=train_transforms)\ntest_data = datasets.ImageFolder(data_dir + '/test1', transform=test_transforms)\n\ntrainloader = torch.utils.data.DataLoader(train_data, batch_size=64, shuffle=True)\ntestloader = torch.utils.data.DataLoader(test_data, batch_size=64)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = models.densenet121(pretrained=True)\nmodel","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n\nmodel = models.densenet121(pretrained=True)\n\n# Freeze parameters so we don't backprop through them\nfor param in model.parameters():\n    param.requires_grad = False\n    \nmodel.classifier = nn.Sequential(nn.Linear(1024, 256),\n                                 nn.ReLU(),\n                                 nn.Dropout(0.2),\n                                 nn.Linear(256, 2),\n                                 nn.LogSoftmax(dim=1))\n\ncriterion = nn.NLLLoss()\n\n# Only train the classifier parameters, feature parameters are frozen\noptimizer = optim.Adam(model.classifier.parameters(), lr=0.003)\n\nmodel.to(device);","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 1\nsteps = 0\nrunning_loss = 0\nprint_every = 5\nfor epoch in range(epochs):\n    for inputs, labels in trainloader:\n        steps += 1\n        # Move input and label tensors to the default device\n        inputs, labels = inputs.to(device), labels.to(device)\n        \n        optimizer.zero_grad()\n        \n        logps = model.forward(inputs)\n        loss = criterion(logps, labels)\n        loss.backward()\n        optimizer.step()\n\n        running_loss += loss.item()\n        \n        if steps % print_every == 0:\n            test_loss = 0\n            accuracy = 0\n            model.eval()\n            with torch.no_grad():\n                for inputs, labels in testloader:\n                    inputs, labels = inputs.to(device), labels.to(device)\n                    logps = model.forward(inputs)\n                    batch_loss = criterion(logps, labels)\n                    \n                    test_loss += batch_loss.item()\n                    \n                    # Calculate accuracy\n                    ps = torch.exp(logps)\n                    top_p, top_class = ps.topk(1, dim=1)\n                    equals = top_class == labels.view(*top_class.shape)\n                    accuracy += torch.mean(equals.type(torch.FloatTensor)).item()\n                    \n            print(f\"Epoch {epoch+1}/{epochs}.. \"\n                  f\"Train loss: {running_loss/print_every:.3f}.. \"\n                  f\"Test loss: {test_loss/len(testloader):.3f}.. \"\n                  f\"Test accuracy: {accuracy/len(testloader):.3f}\")\n            running_loss = 0\n            model.train()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}