由就地操作修改的变量之一

Question

我对Pytorch比较陌生。这里我想使用这个模型来生成一些图像，但是因为这是在Pytorch 1.5之前编写的，因为梯度计算已经被修复，所以这是错误消息

RuntimeError: one of the variables needed for gradient computation has been 
modified by an inplace operation: [torch.cuda.FloatTensor [1, 512, 4, 4]] 
is at version 2; expected version 1 instead. 
Hint: enable anomaly detection to find the operation that 
failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

我看了过去的例子，不确定这里的问题是什么，我相信这是发生在这个地区，但我不知道在哪里！任何帮助都将不胜感激

def process(self, images, edges, masks):
self.iteration += 1

    # zero optimizers
    self.gen_optimizer.zero_grad()
    self.dis_optimizer.zero_grad()


    # process outputs
    outputs = self(images, edges, masks)
    gen_loss = 0
    dis_loss = 0


    # discriminator loss
    dis_input_real = torch.cat((images, edges), dim=1)
    dis_input_fake = torch.cat((images, outputs.detach()), dim=1)
    dis_real, dis_real_feat = self.discriminator(dis_input_real)        # in: (grayscale(1) + edge(1))
    dis_fake, dis_fake_feat = self.discriminator(dis_input_fake)        # in: (grayscale(1) + edge(1))
    dis_real_loss = self.adversarial_loss(dis_real, True, True)
    dis_fake_loss = self.adversarial_loss(dis_fake, False, True)
    dis_loss += (dis_real_loss + dis_fake_loss) / 2


    # generator adversarial loss
    gen_input_fake = torch.cat((images, outputs), dim=1)
    gen_fake, gen_fake_feat = self.discriminator(gen_input_fake)        # in: (grayscale(1) + edge(1))
    gen_gan_loss = self.adversarial_loss(gen_fake, True, False)
    gen_loss += gen_gan_loss


    # generator feature matching loss
    gen_fm_loss = 0
    for i in range(len(dis_real_feat)):
        gen_fm_loss += self.l1_loss(gen_fake_feat[i], dis_real_feat[i].detach())
    gen_fm_loss = gen_fm_loss * self.config.FM_LOSS_WEIGHT
    gen_loss += gen_fm_loss


    # create logs
    logs = [
        ("l_d1", dis_loss.item()),
        ("l_g1", gen_gan_loss.item()),
        ("l_fm", gen_fm_loss.item()),
    ]

    return outputs, gen_loss, dis_loss, logs

def forward(self, images, edges, masks):
    edges_masked = (edges * (1 - masks))
    images_masked = (images * (1 - masks)) + masks
    inputs = torch.cat((images_masked, edges_masked, masks), dim=1)
    outputs = self.generator(inputs)                                    # in: [grayscale(1) + edge(1) + mask(1)]
    return outputs

def backward(self, gen_loss=None, dis_loss=None):
    if dis_loss is not None:
        dis_loss.backward()
    self.dis_optimizer.step()

    if gen_loss is not None:
        gen_loss.backward()
    self.gen_optimizer.step()

谢谢大家!

Answer 1

您不能一次计算鉴别器和生成器的损失，而是让两个反向传播像这样背对背：

if dis_loss is not None:
    dis_loss.backward()
self.dis_optimizer.step()

if gen_loss is not None:
    gen_loss.backward()
self.gen_optimizer.step()

原因如下：当您调用self.dis_optimizer.step()时，您有效地修改了鉴别器的参数，这与您试图反向传播的gen_loss的计算参数相同。这是不可能的

您必须计算dis_loss反向传播，更新鉴别器的权重，并清除梯度。只有这样，您才能使用新更新的鉴别器权重计算gen_loss。最后，在生成器上反向传播

本tutorial是对典型的GAN训练的一个很好的演练