{"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"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":84616,"databundleVersionId":9494719,"sourceType":"competition"}],"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"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\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 read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch\nfrom torch.utils.tensorboard.summary import image\nimport torchvision\nimport torch.nn as nn\nimport torchvision.transforms as transforms\nimport torch.optim as optim\nfrom torch.utils.data import DataLoader\n\n\ntransforms = transforms.Compose([\n    transforms.Resize((224, 224)),\n    transforms.RandomHorizontalFlip(p=0.5),\n    transforms.ToTensor(),\n    transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])\n\ntrain_dataset = torchvision.datasets.CIFAR10(root='./cifar-10-python/', train=True, download=True,\n                                             transform=transforms)\ntrain_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True, num_workers=0)\n\ntest_dataset = torchvision.datasets.CIFAR10(root='./cifar-10-python/', train=False, download=True,\n                                            transform=transforms)\ntest_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=True, num_workers=0)\n\nwei = torchvision.models.ResNet50_Weights.IMAGENET1K_V2\nnet = torchvision.models.resnet50(weights=wei)\n\ninchannel = net.fc.in_features\nnet.fc = nn.Linear(inchannel, 10)\n\ndevice = torch.device(\"cuda:0\")\nnet = net.to(device)\na = 0\nlearning_rate = 0.001\noptimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9)\nmyLoss = torch.nn.CrossEntropyLoss()\n\nfor _epoch in range(10):\n    training_loss = 0.0\n    for _step, input_data in enumerate(train_loader):\n        image, label = input_data[0].to(device), input_data[1].to(device)\n        predict_label = net.forward(image)\n\n        loss = myLoss(predict_label, label)\n\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n\n        training_loss = training_loss + loss.item()\n        if _step % 10 == 0:\n            print('training loss: %.4f' % (training_loss / 10))\n            training_loss = 0.0\n            print()\n            \n    correct = 0\n    total = 0\n\n    net.eval()\n    for images, labels in test_loader:\n        images = images.to(device)\n        labels = labels.to(device)\n        outputs = net(images)\n        numbers, predicted = torch.max(outputs.data, 1)\n        total += labels.size(0)\n        correct += (predicted == labels).sum().item()\n    if correct > a:\n        a = correct\n        torch.save(net.state_dict(),'cifar10_resnet.pth')\n        \n\n    print('Testing Accuracy : %.3f %%' % (100 * correct / total))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"net.to(device)\nnet.load_state_dict(torch.load('cifar10_resnet.pth'))\nnet.eval()","metadata":{},"execution_count":null,"outputs":[]}]}