{"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\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import torch\nimport torchvision.datasets as data\nimport torchvision.transforms as transforms\nimport random\n\nimport pandas as pd\nimport numpy as np\n\nimport torch\nimport torchvision.datasets as data\nimport torchvision.transforms as transforms\nimport random\n\nfrom sklearn import preprocessing","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = 'cuda' if torch.cuda.is_available() else 'cpu'\n\nrandom.seed(777)\ntorch.manual_seed(777)\nif device == 'cuda':\n  torch.cuda.manual_seed_all(777)\n\n# 학습 파라미터 설정\nlearning_rate = 0.01\ntraining_epochs = 15\nbatch_size = 100\nScaler = preprocessing.StandardScaler()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data=pd.read_csv('/kaggle/input/2020-ai-exam-fashionmnist-4/mnist_train_label.csv',header=None,usecols=range(0,784))\ntest_data=pd.read_csv('/kaggle/input/2020-ai-exam-fashionmnist-4/mnist_test.csv',header=None,usecols=range(1,785))\n\nx_train_data=train_data.loc[:,1:785]\ny_train_data=train_data.loc[:,0]\n\nx_train_data=np.array(x_train_data)\ny_train_data=np.array(y_train_data)\nx_train_data = Scaler.fit_transform(x_train_data)\n\nx_train_data=torch.FloatTensor(x_train_data)\ny_train_data=torch.LongTensor(y_train_data)\n\nprint(x_train_data.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = torch.utils.data.TensorDataset(x_train_data, y_train_data)\n\ndata_loader = torch.utils.data.DataLoader(dataset=train_dataset,\n                                          batch_size=batch_size,\n                                          shuffle=True,\n                                          drop_last=True)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"linear1 = torch.nn.Linear(783,512,bias=True)\nlinear2 = torch.nn.Linear(512,512,bias=True)\nlinear3 = torch.nn.Linear(512,512,bias=True)\nlinear4 = torch.nn.Linear(512,512,bias=True)\nlinear5 = torch.nn.Linear(512,10,bias=True)\nrelu = torch.nn.ReLU()\ndropout = torch.nn.Dropout(p=0.3)\n\n# Random Init => Xavier Init\ntorch.nn.init.xavier_uniform_(linear1.weight)\ntorch.nn.init.xavier_uniform_(linear2.weight)\ntorch.nn.init.xavier_uniform_(linear3.weight)\ntorch.nn.init.xavier_uniform_(linear4.weight)\ntorch.nn.init.xavier_uniform_(linear5.weight)\n\nmodel = torch.nn.Sequential(linear1,relu,dropout,\n                            linear2,relu,dropout,\n                            linear3,relu,dropout,\n                            linear4,relu,dropout,\n                            linear5).to(device)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss = torch.nn.CrossEntropyLoss().to(device) # softmax 내부적으로 계산\noptimizer = torch.optim.Adam(model.parameters(), lr=learning_rate) \n\ntotal_batch = len(data_loader)\nmodel.train() # 주의사항 drop_out = True\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, 783).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    model.eval()  # 주의사항 (dropout=False)\n    x_test_data=test_data.loc[:,1:785]\n    x_test_data=np.array(x_test_data)\n    print(x_test_data.shape)\n    x_test_data = Scaler.fit_transform(x_test_data)\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)\n\n\nprint(correct_prediction)\n\nsubmit=pd.read_csv('/kaggle/input/2020-ai-exam-fashionmnist-4/submission.csv')","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()\nprint(submit.dtypes)\n\nsubmit\n\nsubmit.to_csv('baseline.csv',index=False,header=True)\n\n!kaggle competitions submit -c 2020-ai-exam-fashionmnist-4 -f submission.csv -m \"Message\"","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":4}