ValueError: Variable generator/Conv/weights/Adam/ does not exist, or was not created with...

错误:

多GPU设置时出现如下错误:ValueError: Variable E_conv0/w/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

原因:

代码中有tf.get_variable_scope().reuse_variables(),但却缺少上下文管理的APItf.varibale_scope().

解决方法:

在设置GPU的位置添加如下命令:with tf.variable_scope(tf.get_variable_scope()) as scope:

with tf.variable_scope(tf.get_variable_scope()) as scope:
    for i in range(args.num_gpus):
        with tf.device('gpu:%d' % i):
            with tf.name_scope("%s_%d" % ('Tower', i)):
            ...
            tf.get_variable_scope().reuse_variables()

参考:https://blog.csdn.net/u012436149/article/details/73555017

猜你喜欢

转载自blog.csdn.net/xinxiang7/article/details/106545119
今日推荐