add script

gpu/train_for_c2net_fail3.py

@@ -0,0 +1,73 @@
+'''
+在训练环境中，代码会自动放在/tmp/code目录下，上传的数据集会自动放在/tmp/dataset目录下，模型下载路径默认在/tmp/output下，请将模型输出位置指定到/tmp/model，
+启智平台界面会提供/tmp/output目录下的文件下载。
+'''
+
+
+from model import Model
+import numpy as np
+import torch
+from torchvision.datasets import mnist
+from torch.nn import CrossEntropyLoss
+from torch.optim import SGD
+from torch.utils.data import DataLoader
+from torchvision.transforms import ToTensor
+import argparse
+
+# Training settings
+parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
+#数据集位置放在/tmp/dataset下
+parser.add_argument('--traindata', default="/tmp/dataset/train" ,help='path to train dataset')
+parser.add_argument('--testdata', default="/tmp/dataset/test" ,help='path to test dataset')
+parser.add_argument('--epoch_size', type=int, default=1, help='how much epoch to train')
+parser.add_argument('--batch_size', type=int, default=256, help='how much batch_size in epoch')
+
+if __name__ == '__main__':
+    args = parser.parse_args()
+    #日志输出
+    print('cuda is available:{}'.format(torch.cuda.is_available()))  
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    batch_size = args.batch_size
+    train_dataset = mnist.MNIST(root=args.traindata, train=True, transform=ToTensor(),download=False)
+    test_dataset = mnist.MNIST(root=args.testdata, train=False, transform=ToTensor(),download=False)
+    train_loader = DataLoader(train_dataset, batch_size=batch_size)
+    test_loader = DataLoader(test_dataset, batch_size=batch_size)
+    model = Model().to(device)
+    sgd = SGD(model.parameters(), lr=1e-1)
+    cost = CrossEntropyLoss()
+    epoch = args.epoch_size
+    #日志输出
+    print('epoch_size is:{}'.format(epoch))
+    for _epoch in range(epoch):
+        print('the {} epoch_size begin'.format(_epoch + 1))
+        model.train()
+        for idx, (train_x, train_label) in enumerate(train_loader):
+            train_x = train_x.to(device)
+            train_label = train_label.to(device)
+            label_np = np.zeros((train_label.shape[0], 10))
+            sgd.zero_grad()
+            predict_y = model(train_x.float())
+            loss = cost(predict_y, train_label.long())
+            if idx % 10 == 0:
+                print('idx: {}, loss: {}'.format(idx, loss.sum().item()))
+            loss.backward()
+            sgd.step()
+
+        correct = 0
+        _sum = 0
+        model.eval()
+        for idx, (test_x, test_label) in enumerate(test_loader):
+            test_x = test_x
+            test_label = test_label
+            predict_y = model(test_x.to(device).float()).detach()
+            predict_ys = np.argmax(predict_y.cpu(), axis=-1)
+            label_np = test_label.numpy()
+            _ = predict_ys == test_label
+            correct += np.sum(_.numpy(), axis=-1)
+            _sum += _.shape[0]
+        #日志输出
+        print('accuracy: {:.2f}'.format(correct / _sum))
+        #模型输出位置放在/tmp/output下
+        torch.save(model, '/tmp/output/mnist_epoch{}_{:.2f}.pkl'.format(_epoch+1, correct / _sum))
+    print("----------this is the end--------")
+    print(a)