gpunpu/gpu_new/train_for_c2net.py

#!/usr/bin/python
#coding=utf-8
'''
If there are Chinese comments in the code，please add at the beginning：
#!/usr/bin/python
#coding=utf-8   

In the training environment, 
the code will be automatically placed in the /tmp/code directory, 
the uploaded dataset will be automatically placed in the /tmp/dataset directory, and 
the model download path is under /tmp/output by default, please specify the model output location to /tmp/model, 
qizhi platform will provide file downloads under the /tmp/output directory.
'''


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')
#The dataset location is placed under /dataset
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, unknown = parser.parse_known_args()
    #log output
    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
    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]
        print('accuracy: {:.2f}'.format(correct / _sum))
        #The model output location is placed under /model
        torch.save(model, '/tmp/output/mnist_epoch{}_{:.2f}.pkl'.format(_epoch+1, correct / _sum))