keras: AttributeError: module 'tensorflow.python.ops.nn' has no attribute 'leaky_relu'

Would you please help me how to add leaky_relu or get rid of this error?

return K.relu(inputs, alpha=self.alpha) File “C:\Users\fi\Anaconda30\envs\tensorflow\lib\site-packages\keras\backend\tensorflow_backend.py”, line 2918, in relu x = tf.nn.leaky_relu(x, alpha) AttributeError: module ‘tensorflow.python.ops.nn’ has no attribute ‘leaky_relu’

and definition of relu in keras version (latest that I downloaded is:) def relu(x, alpha=0., max_value=None): “”"Rectified linear unit.

With default values, it returns element-wise `max(x, 0)`.

# Arguments
    x: A tensor or variable.
    alpha: A scalar, slope of negative section (default=`0.`).
    max_value: Saturation threshold.

# Returns
    A tensor.
"""
if alpha != 0.:
    x = tf.nn.leaky_relu(x, alpha)
else:
    x = tf.nn.relu(x)

if max_value is not None:
    max_value = _to_tensor(max_value, x.dtype.base_dtype)
    x = tf.minimum(x, max_value)
return x

About this issue

Original URL
State: closed
Created 6 years ago
Reactions: 14
Comments: 16

Most upvoted comments

It works on 2.1.2, for the time being I rolled back to that version.

+20

jjmossel on Feb 12, 2018

Works after upgrading to TF 1.5.0. What could be done about this? Better error message in Keras indicating too old TF version?

hmeine on Feb 13, 2018

I have faced the same problem. switched back to 2.1.2.

sjishan on Mar 8, 2018

@nyck33 I downgraded my keras version using : conda install -c conda keras==2.1.2

cymon1997 on May 16, 2018

For me tf was 1.3 and the error was removed after upgrading to 1.5 using conda forge.

monajalal on Mar 25, 2018

'''
Written by Hans Meine to reproduce
AttributeError: module 'tensorflow.python.ops.nn' has no attribute 'leaky_relu'
'''

import tensorflow, keras
print(tensorflow.__version__, keras.__version__)

from keras.models import Sequential
from keras.layers import LeakyReLU
from keras.layers import InputLayer

m = Sequential()
m.add(InputLayer(input_shape=(1000,)))
m.add(LeakyReLU(alpha=0.2))

hmeine on Feb 11, 2018