参考莫烦python:
import torchimport torch.utils.data as Dataimport matplotlib.pyplot as pltimport torch.nn.functional as Fimport torch.nn as nnimport torchvision EPOCH = 1BATCH_SIZE = 50LR = 0.01DOWNLOAD_MNIST = False train_data = torchvision.datasets.MNIST( root = './minst/', train=True, transform=torchvision.transforms.ToTensor(), download=DOWNLOAD_MNIST )# plt.imshow(train_data.train_data[0].numpy(), cmap='gray')# plt.title('%i' % train_data.train_data_labels[0])# plt.show()train_loader = Data.DataLoader(train_data, batch_size=BATCH_SIZE, shuffle=True) test_data = torchvision.datasets.MNIST(root='./minst/', train=False) test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255. # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)test_y = test_data.test_labels[:2000]class CNN(nn.Module):def __init__(self): super(CNN, self).__init__() self.conv1 = nn.Sequential( #1 * 16 * 16 nn.Conv2d( in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2, ), #16 * 28 * 28 nn.ReLU(), nn.MaxPool2d(kernel_size=2), #16 * 14 * 14 ) self.conv2 = nn.Sequential( nn.Conv2d(16, 32, 5, 1, 2), #32 * 14 * 14 nn.ReLU(), nn.MaxPool2d(2) #32 * 7 * 7 ) self.out = nn.Linear(32 * 7 * 7, 10)def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = x.view(x.size(0), -1) #压缩图像成一维output = self.out(x)return output cnn = CNN()print(cnn) optimizer = torch.optim.Adam(cnn.parameters(), lr=LR) # optimize all cnn parametersloss_func = nn.CrossEntropyLoss() # the target label is not one-hotted# training and testingfor epoch in range(EPOCH):for step, (b_x, b_y) in enumerate(train_loader): # 分配 batch data, normalize x when iterate train_loaderoutput = cnn(b_x) # cnn outputloss = loss_func(output, b_y) # cross entropy lossoptimizer.zero_grad() # clear gradients for this training steploss.backward() # backpropagation, compute gradientsoptimizer.step() # apply gradientsif step % 50 == 0: test_output = cnn(test_x) pred_y = torch.max(test_output, 1)[1].data.squeeze() accuracy = sum(pred_y == test_y) / float(test_y.size(0))print('Epoch:', epoch, '|train loss: %.4f' % loss.data)print('|accuracy: %.4f' % accuracy) test_output = cnn(test_x[:10]) pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()print(pred_y, 'prediction number')print(test_y[:10].numpy(), 'real number')