python - 传递给 Optimizer.compute_gradients 的 `loss` 应该是启用急切执行时的函数

Question

我是 TensorFlow 的新手，我才刚刚开始学习和理解它。我正在处理神经风格迁移问题，我正在使用 tensorflow 1.14 版。

我收到一个错误传递给优化器的损失。compute_gradients 应该是启用急切执行时的一个函数。

我试图通过使用 TensorFlow 图形而不是 eager execution 来解决问题，但它不起作用。我想使用 eager execution 因为它看起来更像 pythonic 方式。

这是我的代码，很抱歉将整个代码放在这里，请在我的代码中提出更正建议。

import scipy
import tensorflow as tf
import tensorflow.contrib.eager as tfe
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
from scipy import misc
from skimage.transform import resize
from tensorflow.keras.applications.vgg19 import VGG19, preprocess_input
from tensorflow.keras import backend as K

tf.enable_eager_execution()
print('Eager execution {}'.format(tf.executing_eagerly()))

content_path = '800px-Green_Sea_Turtle_grazing_seagrass.jpg'
style_path = '800px-The_Great_Wave_off_Kanagawa.jpg'

content_img = plt.imread(content_path)
plt.imshow(content_img)
style_img = plt.imread(style_path)
plt.imshow(style_img)

MEANS = np.array([123.68, 116.779, 103.939]).reshape((1,1,1,3))
content_img = resize(content_img, (552,800,3)) #resized content img because style img has shape (552,800,3)

content_img = np.array(content_img)
content_img = np.reshape(content_img, ((1,)+content_img.shape))
style_img = np.array(style_img)
style_img = np.reshape(style_img, ((1,)+style_img.shape))

noise_img= np.random.uniform(-20,20,(1,552,800,3)).astype('float32')
generated_img = noise_img*0.6 + content_img*0.4
plt.imshow(generated_img[0])

content_img = content_img-MEANS
style_img = style_img-MEANS

model = VGG19(include_top=False, weights='imagenet')

def compute_content_cost(act_content_img, act_generated_img):
    return tf.reduce_mean(tf.square(act_content_img-act_generated_img))

def gram_matrix(A):
    gram = tf.matmul(A, tf.transpose(A))
    return gram

def style_loss_one_layer(act_style_img, act_generated_img):
    m,n_H,n_W,n_C = tf.shape(act_generated_img)               #act_generated_img.get_shape().as_list()
    gram_act_style_img = gram_matrix(act_style_img)
    gram_generated_img = gram_matrix(act_generated_img)
    return tf.reduce_mean(tf.square(gram_act_style_img-gram_generated_img))*(1/(4*n_C**2*(n_H*n_W)**2))

content_layer = ['block5_conv2']
style_layers = [('block1_conv1',0.2), 
                ('block2_conv1',0.2),
                ('block3_conv1',0.2),
                ('block4_conv1',0.2),
                ('block5_conv1',0.2)]

def compute_style_cost(model, style_layers):
    style_cost = total_style_cost = 0
    for layer, coeff in style_layers:
        act_style_img = model.get_layer(layer).output
        act_generated_img = model.get_layer(layer).output
        style_cost += style_loss_one_layer(act_style_img, act_generated_img)
        total_style_cost += coeff*style_cost 
    return total_style_cost

def compute_total_cost(J_content, J_style, alpha=10, beta=40):
    J = (alpha*tf.cast(J_content, tf.float64)) + (beta*J_style)
    return J

act_generated_img = model.get_layer('block5_conv2').output
act_content_img = model.get_layer('block5_conv2').output

J_content = compute_content_cost(act_content_img=act_content_img, act_generated_img=act_generated_img)
print(J_content)
J_style = compute_style_cost(model, style_layers=style_layers)
print(J_style)

J_total_cost = compute_total_cost(J_content, J_style, alpha=10, beta=40)
print(J_total_cost)

optimizer = tf.train.AdamOptimizer(2.0)

train_step = optimizer.minimize(J_total_cost)        #**getting error here**

Answer 1

以上错误主要是当你尝试使用TensorFlow 1.x但系统运行的是tensor 2.0时导致的。

使用下面的代码初始化 TensorFlow 以确保您正在尝试使用版本 1.0

import tensorflow.compat.v1 as tf

您可以在初始化程序后通过以下命令使系统禁用该行为。

tf.disable_v2_behavior()