{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","collapsed":true,"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":false},"cell_type":"code","source":"! mkdir -p ~/.kaggle\n! cp kaggle.json ~/.kaggle/\n! chmod 600 ~/.kaggle/kaggle.json","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"! pip uninstall --y kaggle\n! pip install --upgrade\n! pip install kaggle==1.5.6","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"! kaggle competitions download -c 2020-ai-exam-fashionmnist-1\n! unzip 2020-ai-exam-fashionmnist-1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport pandas as pd\nimport numpy as np\nimport random\nfrom sklearn import preprocessing\n#import matplotlib.pyplot as plt\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = 'cuda' if torch.cuda.is_available() else 'cpu'\n! nvidia-smi\n\nrandom.seed(777)\ntorch.manual_seed(777)\nif device == 'cuda':\n  torch.cuda.manual_seed_all(777)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n# 학습 파라미터 설정\nlearning_rate = 0.001\ntraining_epochs = 15\nbatch_size = 100","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data=pd.read_csv('mnist_train_label.csv',header=None, usecols=range(0,785))\ntest_data=pd.read_csv('mnist_test.csv',header=None, usecols=range(0,784))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nx_data = train_data.loc[:,1:]\ny_data = train_data.loc[:,[0]]\nx_data = np.array(x_data)\ny_data = np.array(y_data)\nx_train = torch.FloatTensor(x_data)\ny_train = torch.LongTensor(y_data).squeeze()\nprint(x_data.shape)\nprint(y_data.shape)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = torch.utils.data.TensorDataset(x_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_loader = torch.utils.data.DataLoader(dataset=train_dataset,\n                                          batch_size=batch_size,\n                                          shuffle=True,\n                                          drop_last=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"linear = torch.nn.Linear(784,10,bias=True) #레이어 한개\ntorch.nn.init.normal_(linear.weight)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = torch.nn.Sequential(linear).to(device) # 레이어 한개 이므로","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 손실함수와 최적화 함수\n# BCELoss()\nloss = torch.nn.CrossEntropyLoss().to(device) # softmax 내부적으로 계산\noptimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, momentum=0.9) #SGD optimizer사용","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntotal_batch = len(data_loader)\nfor epoch in range(training_epochs):\n    avg_cost = 0\n\n    for X, Y in data_loader:\n\n        # (1000, 1, 28, 28) 크기의 텐서를 (1000, 784) 크기의 텐서로 변형\n        X = X.view(-1, 28 * 28).to(device)\n        # one-hot encoding되어 있지 않음\n        Y = Y.to(device)\n        #%debug\n\n        # 그래디언트 초기화\n        optimizer.zero_grad()\n        # Forward 계산\n        hypothesis = model(X)\n        # Error 계산\n        cost = loss(hypothesis, Y)\n        # Backparopagation\n        cost.backward()\n        # 가중치 갱신\n        optimizer.step()\n\n        # 평균 Error 계산\n        avg_cost += cost / total_batch\n\n    print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))\n\nprint('Learning finished')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Test the model using test sets\nwith torch.no_grad():\n\n  x_test_data=test_data.loc[:,:]\n  x_test_data=np.array(x_test_data)\n  #x_test_data = Scaler.transform(x_test_data)\n  x_test_data = torch.FloatTensor(x_test_data).to(device)\n\n\n  #x_test_data=torch.from_numpy(x_test_data).float().to(device)\n\n  prediction = model(x_test_data)\n  correct_prediction = torch.argmax(prediction, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"correct_prediction = correct_prediction.cpu().numpy().reshape(-1,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submit=pd.read_csv('submission.csv')\nsubmit","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in range(len(correct_prediction)):\n  submit['Category'][i] = correct_prediction[i].item()\nsubmit.to_csv('submit.csv',index=False,header=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"! kaggle competitions submit -c 2020-ai-exam-fashionmnist-1 -f submit.csv -m \".\"","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":4}