tf.nn.dropout() 警报信息处理

最新推荐文章于 2022-01-09 22:26:19 发布

xuan9719

最新推荐文章于 2022-01-09 22:26:19 发布

阅读量8.4k

点赞数 11

CC 4.0 BY-SA版权

分类专栏： tensorflow版本更新踩坑文章标签： tensorflow tf.nn.drop keep_prob instructions for updating

本文链接：https://blog.youkuaiyun.com/xuan9719/article/details/99643315

在TensorFlow中，使用tf.nn.dropout()时出现关于keep_prob参数的弃用警告。官方建议更新为使用rate参数，即1-keep_prob。本文解释了dropout函数的内部工作原理，包括keep_prob和rate的区别，并提供了如何消除警告的代码示例。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

WARNING: Logging before flag parsing goes to stderr.
calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use ‘rate’ instead of ‘keep_prob’. Rate should be set to ‘rate = 1 - keep_prob’.

tf.nn.dropout() 源码如下：

def dropout(x, keep_prob=None, noise_shape=None, seed=None, name=None, rate=None):
    '''官方备注节选
    Args:
    x: A floating point tensor.
    keep_prob: (deprecated) A deprecated alias for `(1-rate)`
    rate: A scalar `Tensor` with the same type as `x`. The probability that each
      element of `x` is discarded.
    '''
    try:
       keep = 1. - keep_prob if keep_prob is not