法一：DataLoader内置数据加载器
import torch.utils.data as Data#数据加载器
torch_dataset = Data.TensorDataset(trainX,trainY) #trainX，trainY是用于训练的数据和标签
loader = Data.DataLoader(dataset=torch_dataset,batch_size=128, #batch_sizeshuffle=True, #True,随机打乱
)print(" Start training... ")
for epoch in range(epochs):loss_sum = 0num = 0for step,(batch_x,batch_y) in enumerate(loader):y_pre = model(batch_x)#y_pre = y_pre.cpu()#batch_y = batch_y.type(torch.FloatTensor)loss = loss_func(y_pre, batch_y)loss_sum = loss_sum + lossnum = num + 1optimizer.zero_grad()loss.backward()optimizer.step()if epoch % 100 == 0:torch.save(model.state_dict(), str(epoch)+'model.pkl')loss_mean = loss_sum / numprint('epoch:', epoch, ' loss:', loss_mean)
法二：yeild函数
def get_batches(self, inputs, targets, batch_size, shuffle=True): #inputs相当于X，targets相当于Ylength = len(inputs)if shuffle: #shuffle 随机打乱index = torch.randperm(length)else:index = torch.LongTensor(range(length))start_idx = 0while (start_idx < length):end_idx = min(length, start_idx + batch_size)excerpt = index[start_idx:end_idx]X = inputs[excerpt]; Y = targets[excerpt];yield Variable(X), Variable(Y);start_idx += batch_sizefor X, Y in data.get_batches(X, Y, batch_size, True):model.zero_grad();output = model(X);loss = loss_func(output, Y);loss.backward();grad_norm = optim.step();total_loss += loss;loss = total_loss/n_samples