我想使用WGAN-GP，当我运行代码时，它会给我一个错误：

def calculate_gradient_penalty(real_images, fake_images):

    t = torch.rand(real_images.size(0), 1, 1, 1).to(real_images.device)
    t = t.expand(real_images.size())

    interpolates = t * real_images + (1 - t) * fake_images
    interpolates.requires_grad_(True)

    disc_interpolates = D(interpolates)

    grad = torch.autograd.grad(
        outputs=disc_interpolates, inputs=interpolates,
        grad_outputs=torch.ones_like(disc_interpolates),
        create_graph=True, retain_graph=True, allow_unused=True)[0]

    grad_norm = torch.norm(torch.flatten(grad, start_dim=1), dim=1)
    loss_gp = torch.mean((grad_norm - 1) ** 2) * lambda_term

    return loss_gp

RuntimeError Traceback（最近一次调用最后一次）中

/opt/conda/lib/python3.8/site-packages/torch/tensor.py（自，梯度，retain_graph，create_graph，输入）243create_graph=create_graph，244输入=输入）--

/opt/conda/lib/python3.8/site-packages/torch/autograd/init.py（张量grad_tensorsretain_graphcreate_graphgrad_variables输入）143retain_graph=create_graph144--

RuntimeError：CUDA内存溢出。尝试分配64.00 MiB（GPU 2；15.75 GiB总容量；13.76 GiB已分配；2.75 MiB免费；PyTorch总共保留14.50 GiB）

列车代码：

%%time

d_progress = []
d_fake_progress = []
d_real_progress = []
penalty = []
g_progress = []

data = get_infinite_batches(benign_data_loader)
one = torch.FloatTensor([1]).to(device) 
mone = (one * -1).to(device) 

for g_iter in range(generator_iters):

    print('----------G Iter-{}----------'.format(g_iter+1))

    for p in D.parameters():
        p.requires_grad = True # This is by Default
    
    d_loss_real = 0
    d_loss_fake = 0
    Wasserstein_D = 0

    for d_iter in range(critic_iter):
        D.zero_grad()
         
        images = data.__next__()
        if images.size()[0] != batch_size:
            continue
    
        # Train Discriminator
        # Real Images
        images = images.to(device)
        z = torch.randn(batch_size, 100, 1, 1).to(device)
        d_loss_real = D(images)
        d_loss_real = d_loss_real.mean(0).view(1)
        d_loss_real.backward(mone)
    
        # Fake Images
        fake_images = G(z)
        d_loss_fake = D(fake_images)
        d_loss_fake = d_loss_fake.mean(0).view(1)
        d_loss_fake.backward(one)
    
        # Calculate Penalty
        gradient_penalty = calculate_gradient_penalty(images.data, fake_images.data)
        gradient_penalty.backward()
    
        # Total Loss
        d_loss = d_loss_fake - d_loss_real + gradient_penalty
        Wasserstein_D = d_loss_real - d_loss_fake
        d_optimizer.step()
        print(f'D Iter:{d_iter+1}/{critic_iter} Loss:{d_loss.detach().cpu().numpy()}')
    
        time.sleep(0.1)
        d_progress.append(d_loss) # Store Loss
        d_fake_progress.append(d_loss_fake)
        d_real_progress.append(d_loss_real)
        penalty.append(gradient_penalty)

    # Generator Updata
    for p in D.parameters():
        p.requires_grad = False  # Avoid Computation

    # Train Generator
    # Compute with Fake
    G.zero_grad()
    z = torch.randn(batch_size, 100, 1, 1).to(device)
    fake_images = G(z)
    g_loss = D(fake_images)
    g_loss = g_loss.mean().mean(0).view(1)
    g_loss.backward(one)
    # g_cost = -g_loss
    g_optimizer.step()
    print(f'G Iter:{g_iter+1}/{generator_iters} Loss:{g_loss.detach().cpu().numpy()}')
    
    g_progress.append(g_loss) # Store Loss    

有人知道如何解决这个问题吗？