1

我从共享变量教程中借用了这个例子：

def my_image_filter(input_images):
    with tf.variable_scope("conv1"):
        # Variables created here will be named "conv1/weights", "conv1/biases".
        relu1 = conv_relu(input_images, [5, 5, 32, 32], [32])
    with tf.variable_scope("conv2"):
        # Variables created here will be named "conv2/weights", "conv2/biases".
        return conv_relu(relu1, [5, 5, 32, 32], [32])

假设我训练了这些变量并保存了所有四个变量：weights以及biasesfromconv1和conv2layers 通过传递var_listto tf.train.Saver。

现在我想恢复并使用它们两次：

with tf.variable_scope("image_filters") as scope:
    result1 = my_image_filter(image1)
    scope.reuse_variables()
    result2 = my_image_filter(image2)

但是变量的名称现在具有image_filters前缀，即image_filters/conv1/weights，因此保护程序无法恢复它们：Key image_filters/conv1/weights not found in checkpoint

如何恢复所有训练过的变量并多次重复使用它们？

4

0 回答 0