day9-图像风格迁移

定义两个间距，一个用于内容，另一个用于风格

测量两张图片内容的不同，而用来测量两张图片风格的不同。然后，我们输入第三张图片，并改变这张图片，使其与内容图片的内容间距和风格图片的风格间距最小化

样式迁移常用的损失函数由3部分组成：内容损失（content loss）使合成图像与内容图像在内容特征上接近，样式损失（style loss）令合成图像与样式图像在样式特征上接近，而总变差损失（total variation loss）则有助于减少合成图像中的噪点。最后，当模型训练结束时，我们输出样式迁移的模型参数，即得到最终的合成图像。

损失函数

内容损失

class ContentLoss(nn.Module):

    def __init__(self, target,):
        super(ContentLoss, self).__init__()
        # we 'detach' the target content from the tree used
        # to dynamically compute the gradient: this is a stated value,
        # not a variable. Otherwise the forward method of the criterion
        # will throw an error.
        self.target = target.detach()

    def forward(self, input):
        self.loss = F.mse_loss(input, self.target)
        return input

风格损失

def gram_matrix(input):
    a, b, c, d = input.size()  # a=batch size(=1)
    # b=number of feature maps
    # (c,d)=dimensions of a f. map (N=c*d)

    features = input.view(a * b, c * d)  # resise F_XL into \hat F_XL

    G = torch.mm(features, features.t())  # compute the gram product

    # we 'normalize' the values of the gram matrix
    # by dividing by the number of element in each feature maps.
    return G.div(a * b * c * d)

class StyleLoss(nn.Module):

    def __init__(self, target_feature):
        super(StyleLoss, self).__init__()
        self.target = gram_matrix(target_feature).detach()

    def forward(self, input):
        G = gram_matrix(input)
        self.loss = F.mse_loss(G, self.target)
        return input