{"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\ndevice = '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\nlearning_rate = 0.001\ntraining_epochs = 15\nbatch_size = 100\ndrop_prob = 0.3\n\nimport pandas as pd\nimport numpy as np\n\ntrain = pd.read_csv('/kaggle/input/2020-ai-exam-fashionmnist-2/mnist_train_label.csv',header=None)\ntest = pd.read_csv('/kaggle/input/2020-ai-exam-fashionmnist-2/mnist_test.csv',header=None)\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train_data=train.loc[:,1:]\ny_train_data=train.loc[:,0]\n\nfrom sklearn import preprocessing\nScaler = preprocessing.StandardScaler()\n\nx_train_data=np.array(x_train_data)\ny_train_data=np.array(y_train_data)\n#x_train_data = Scaler.fit_transform(x_train_data)\nx_train_data=torch.FloatTensor(x_train_data)\ny_train_data=torch.LongTensor(y_train_data)\n\ntrain_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\nlinear1 = torch.nn.Linear(784,10,bias=True)\nrelu = torch.nn.ReLU()\n\ntorch.nn.init.xavier_normal_(linear1.weight)\n\nmodel = torch.nn.Sequential(linear1).to(device)\n\nloss = torch.nn.CrossEntropyLoss().to(device)\noptimizer = torch.optim.SGD(model.parameters(), lr=learning_rate,momentum=0.9) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"total_batch = len(data_loader)\nfor epoch in range(training_epochs):\n    avg_cost = 0\n\n    for X, Y in data_loader:\n\n        X = X.view(-1, 28 * 28).to(device)\n\n        Y = Y.to(device)\n\n        optimizer.zero_grad()\n\n        hypothesis = model(X)\n    \n        cost = loss(hypothesis, Y)\n        cost.backward()\n        optimizer.step()\n\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":"with torch.no_grad():\n\n  x_test_data=test.loc[:,:]\n  x_test_data=np.array(x_test_data)\n  #x_test_data = Scaler.transform(x_test_data)\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('/kaggle/input/2020-ai-exam-fashionmnist-2/submission.csv')","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}