pytorch训练时的显存占用递增的问题解决

model.eval()
with torch.no_grad():
        for idx, (data, target) in enumerate(data_loader):
            if args.gpu != -1:
                data, target = data.to(args.device), target.to(args.device)
            log_probs = net_g(data)
            probs.append(log_probs)
            
            # sum up batch loss
            test_loss += F.cross_entropy(log_probs, target, reduction='sum').item()
            # get the index of the max log-probability
            y_pred = log_probs.data.max(1, keepdim=True)[1]
            correct += y_pred.eq(target.data.view_as(y_pred)).long().cpu().sum()

torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True

"""添加了最后两行，img和segm是图像和标签输入，很明显通过.cuda()已经是被存在在显存里了；
   outputs是模型的输出，模型在显存里当然其输出也在显存里；loss是通过在显存里的segm和
   outputs算出来的，其也在显存里。这4个对象都是一次性的，使用后应及时把其从显存中清除
   （当然如果你显存够大也可以忽略）。"""
 
def train(model, data_loader, batch_size, optimizer):
    model.train()
    total_loss = 0
    accumulated_steps = 32 // batch_size
    optimizer.zero_grad()
    for idx, (img, segm) in enumerate(tqdm(data_loader)):
        img = img.cuda()
        segm = segm.cuda()
        outputs = model(img)
        loss = criterion(outputs, segm)
        (loss/accumulated_steps).backward()
        if (idx + 1 ) % accumulated_steps == 0:
            optimizer.step() 
            optimizer.zero_grad()
        total_loss += loss.item()
        
        # delete caches
        del img, segm, outputs, loss
        torch.cuda.empty_cache()

def train(model,epochs,data):
    for e in range(epochs):
        print("1:{}".fORMat(torch.cuda.memory_allocated(0)))
        train_epoch(model,data)
        print("2:{}".format(torch.cuda.memory_allocated(0)))
        eval(model,data)
        print("3:{}".format(torch.cuda.memory_allocated(0)))

def train_epoch(model,data):
    model.train()
    optim=torch.optimizer()
    for batch_data in data:
        print("1:{}".format(torch.cuda.memory_allocated(0)))
        output=model(batch_data)
        print("2:{}".format(torch.cuda.memory_allocated(0)))
        loss=loss(output,data.target)
        print("3:{}".format(torch.cuda.memory_allocated(0)))
        optim.zero_grad()
        print("4:{}".format(torch.cuda.memory_allocated(0)))
        loss.backward()
        print("5:{}".format(torch.cuda.memory_allocated(0)))
        utils.func(model)
        print("6:{}".format(torch.cuda.memory_allocated(0)))

def func(model):
    print("1:{}".format(torch.cuda.memory_allocated(0)))
    a=f1(model)
    print("2:{}".format(torch.cuda.memory_allocated(0)))
    b=f2(a)
    print("3:{}".format(torch.cuda.memory_allocated(0)))
    c=f3(b)
    print("4:{}".format(torch.cuda.memory_allocated(0)))
    d=f4(c)
    print("5:{}".format(torch.cuda.memory_allocated(0)))