样式损失始终为零

如何解决样式损失始终为零

我正在尝试在模型上使用特征重建和样式重建损失。为此，我遵循了PyTorch网站上“神经样式转换”的示例代码。

https://pytorch.org/tutorials/advanced/neural_style_tutorial.html

尽管可以毫无问题地计算出特征损失，但样式损失始终为零。而且我找不到原因，因为在执行过程中一切看起来都很好。这些损失函数的计算方法与所提出的数学方法相同。此外，如您所知，样式和特征损失在计算方面几乎相同，除了Gram矩阵逐步减少样式损失且特征损失没有问题。

有人能帮助我解决这种情况吗？

class Feature_and_style_losses():
def __init__(self,):
    self.vgg_model = models.vgg19(pretrained=True).features.cuda().eval()
    self.content_layers = ['conv_16']
    self.style_layers = ['conv_5']

def calculate_feature_and_style_losses(self,input_,target,feature_coefficient,style_coefficient):
    i = 0
    feature_losses = []
    style_losses = []
    for layer_ in self.vgg_model.children():
        if isinstance(layer_,nn.Conv2d):
            i += 1
            name = "conv_{}".format(i)

            if name in self.content_layers:
                features_input = self.vgg_model(input_).detach()
                features_target = self.vgg_model(target).detach()
                feature_losses.append(self.feature_loss(features_input,features_target))
            if name in self.style_layers:
                style_input = self.vgg_model(input_).detach()
                style_target = self.vgg_model(target).detach()
                style_losses.append(self.style_loss(style_input,style_target))

    feature_loss_value = (torch.mean(torch.from_numpy(np.array(feature_losses,dtype=np.float32)))) * feature_coefficient
    style_loss_value = (torch.mean(torch.from_numpy(np.array(style_losses,dtype=np.float32)))) * style_coefficient

    return feature_loss_value,style_loss_value

def feature_loss(self,target):
    target = target.detach()
    feature_reconstruction_loss = F.mse_loss(input_,target)
    return feature_reconstruction_loss

def gram_matrix(self,input_):
    a,b,c,d = input_.size() #??? check size
    features = input_.view(a*b,c*d)
    #features_t = features.transpose(1,2)
    #G = features.bmm(features_t) / (b*c*d)
    #print(features.shape)
    G = torch.mm(features,features.t())
    return G.div(a*b*c*d)
    return G

def style_loss(self,target):
    G_input = self.gram_matrix(input_)
    G_target = self.gram_matrix(target).detach()
    #style_reconstruction_loss = self.feature_loss(G_input,G_target)
    style_reconstruction_loss = F.mse_loss(G_input,G_target)
    return style_reconstruction_loss

---

feature_loss_ = Feature_and_style_losses()
...
for e in range(epochs):
    for i,batch in enumerate(DataLoader):
        ...
        real_C = Variable(batch["C"].type(Tensor))
        fake_C = independent_decoder(features_all)    
        f_loss,s_loss = feature_loss_.calculate_feature_and_style_losses(fake_C,real_C,1,10)
        loss_G_3 = loss_GAN_3 + lambda_pixel * (loss_pixel_3_object + loss_pixel_3_scene) * 0.5 + f_loss + s_loss
        loss_G_3.backward(retain_graph=True)
        optimizer_independent_decoder.step()

最好。