出现这个问题,有几种解决办法,可以调低一下keras的版本,比如:

pip install keras==2.1

不过还有个更方便的方法,从错误可知softmax中不包含axis这个参数,那么把axis参数替换成dim就可以了。源代码是这样的:

def softmax(x, axis=-1):
    """Softmax of a tensor.

    # Arguments
        x: A tensor or variable.
        axis: The dimension softmax would be performed on.
            The default is -1 which indicates the last dimension.

    # Returns
        A tensor.
    """
    return tf.nn.softmax(x, axis=axis)

更改成这样:

def softmax(x, axis=-1):
    """Softmax of a tensor.

    # Arguments
        x: A tensor or variable.
        axis: The dimension softmax would be performed on.
            The default is -1 which indicates the last dimension.

    # Returns
        A tensor.
    """
    return tf.nn.softmax(x, dim=axis)

就是改了最后一行。

相关文章:

  • 2021-11-19
  • 2022-03-07
  • 2021-12-02
  • 2021-06-28
  • 2022-12-23
  • 2022-12-23
  • 2022-12-23
  • 2022-12-23
猜你喜欢
  • 2021-07-28
  • 2021-06-05
  • 2022-12-23
  • 2021-08-30
  • 2021-10-29
  • 2022-12-23
  • 2022-12-23
相关资源
相似解决方案