Keras 神经风格迁移：backend.gradients 返回无答案

【问题标题】：Keras Neural Style Transfer: backend.gradients returns NoneKeras 神经风格迁移：backend.gradients 返回无
【发布时间】：2018-07-21 09:58:40
【问题描述】：

我正在尝试使用 Keras 实现神经风格迁移，并尝试使其尽可能简单。尝试使用 keras 的 backend.gradients() 函数查找梯度时，它返回 [None]。我的代码如下：

content_image = cv2.imread("C:/Users/Max/Desktop/IMG_20170331_103755.jpg") 
content_image = cv2.resize(content_image, (512,512))
style_image = cv2.imread("C:/Users/Max/Desktop/starry.jpg")
style_image = cv2.resize(style_image, (512,512))

content_array = np.asarray(content_image, dtype=np.float32)
content_array = np.expand_dims(content_array, axis=0)

style_array = np.asarray(style_image, dtype=np.float32)
style_array = np.expand_dims(style_array, axis=0)

# Constants:

epochs = 1
height = 512
width = 512
num_channels = 3
step_size = 10

content_layer = ['block2_conv2']
style_layer = ['block1_conv2', 'block2_conv2', 'block3_conv3','block4_conv3', 'block5_conv3']

loss_total = backend.variable(0.0)

# VGG16 Model:

model = VGG16(input_shape = [height, width, num_channels],weights='imagenet', include_top=False)

# Defining losses:

def content_loss(Content, Mixed):
    content_loss = backend.mean(backend.square(Mixed - Content))
    return content_loss

def gram(layer):
    flat = backend.reshape(layer, shape=[1, -1])
    gram = backend.dot(flat, backend.transpose(flat))
    return gram

def style_loss(Style, Mixed):
    S_G = gram(Style)
    M_G = gram(Mixed)
    size = height*width
    return backend.sum(backend.square(S_G - M_G)) / (4. * (num_channels ** 2) * (size ** 2))
'''
def denoise(Image):
    loss = backend.mean(backend.abs(Image[:,1:,:,:] - Image[:,:-1,:,:]) +     backend.abs(Image[:,:,1:,:] - Image[:,:,:-1,:]))
    return loss
'''
# Backend Functions:

output_c = backend.function(inputs = [model.layers[0].input] , outputs = [model.get_layer(content_layer[0]).output])
output_s = backend.function(inputs = [model.layers[0].input] , outputs = [model.get_layer(layer).output for layer in style_layer])

content_output = output_c([content_array])
style_output = output_s([style_array])

# Randomly generated image:

Mixed = np.random.uniform(0, 255, [1, height, width, 3]) - 128

# Loop:

for i in range(epochs):

    mixed_c = output_c([Mixed])
    mixed_c = mixed_c[0]

    loss_c = content_loss(content_output[0], mixed_c)

    total = []
    mixed_s = output_s([Mixed])
    for i in range(len(style_layer)):
        style = style_loss(style_output[i], mixed_s[i])
        total.append(style)
        loss_s = backend.sum(total)
    #loss_d = denoise(Mixed)
    loss_total = w_c * loss_c + w_s * loss_s #+ w_d * loss_d
    gradient = backend.gradients(loss_total, Mixed)
    gradient = np.squeeze(gradient)
    step_size = step_size / (np.std(gradient) + 1e-8)
    Mixed -= gradient * step_size

我应该进行哪些更改才能使渐变正常工作。我不知道出了什么问题。

谢谢！

【问题讨论】：

尝试打印出单个值：loss_total、w_c、loss_c、w_s、loss_s

标签： python-3.x deep-learning keras conv-neural-network

【解决方案1】：

您正在采用 Mixed 的梯度，这是一个 numpy 数组而不是变量。您需要定义一个张量，然后其值为Mixed。

来自 Keras 文档：

渐变

keras.backend.gradients(loss, variables)

返回variables w.r.t 的梯度。 loss.

参数

loss：要最小化的标量张量。

变量：变量列表。

【讨论】：