深度学习基础：with torch.no_grad()或@torch.no_grad() 用法

1.requires_grad=True 要求计算梯度

2.requires_grad=False 不要求计算梯度

3.with torch.no_grad()或者@torch.no_grad()中的数据不需要计算梯度，也不会进行方向传播。

 

@torch.no_grad()
def evaluate(model, data_loader, device, epoch):
    loss_function = torch.nn.CrossEntropyLoss()

    model.eval()

    accu_num = torch.zeros(1).to(device)   # 累计预测正确的样本数
    accu_loss = torch.zeros(1).to(device)  # 累计损失

    sample_num = 0
    data_loader = tqdm(data_loader, file=sys.stdout)
    for step, data in enumerate(data_loader):
        images, labels = data
        sample_num += images.shape[0]

        pred = model(images.to(device))
        pred_classes = torch.max(pred, dim=1)[1]
        accu_num += torch.eq(pred_classes, labels.to(device)).sum()

        loss = loss_function(pred, labels.to(device))
        accu_loss += loss

        data_loader.desc = "[valid epoch {}] loss: {:.3f}, acc: {:.3f}".format(epoch,
                                                                               accu_loss.item() / (step + 1),
                                                                               accu_num.item() / sample_num)

    return accu_loss.item() / (step + 1), accu_num.item() / sample_num