Recommendation for the softmax() got an unexpected keyword argument 'axis' error

Question

Here is the program I run:

out_layer = tf.add(tf.matmul(layer_4 , weights['out']) , biases['out'])
 out_layer = tf.nn.softmax(out_layer)

model=Sequential()
 
 model.add(Dense(100, input_dim= n_dim, 
 activation='tanh',kernel_initializer='uniform'))
 keras.layers.core.Dropout(0.3, noise_shape=None, seed=None)
 
 model.add(Dense(50,input_dim=1000,activation='sigmoid'))
 keras.layers.core.Dropout(0.4, noise_shape=None, seed=None)
 
 model.add(Dense(15,input_dim=500,activation='sigmoid'))
 keras.layers.core.Dropout(0.2, noise_shape=None, seed=None)
 
 model.add(Dense(units=n_class))
 model.add(Activation('softmax'))

After I run, it returns an error:

TypeError: softmax() got an unexpected keyword argument 'axis'

Does anyone have any suggestions for the problem below: softmax() got an unexpected keyword argument 'axis' in the python - How to correct it?

dttutoria · Accepted Answer

The cause: Tensorflow and Keras version mismatch is reported as the cause of the softmax() got an unexpected keyword argument ‘axis’ error. Solution: Use:

import tensorflow as tf

Afterwards, apply a softmax layer as follows:

model.add(Activation(tf.nn.softmax))

Hugo Pasquier · Answer

Upgrading your Keras and tensoflow libraries to the latest versions is recommended. Lower versions don't support softmax axis. It is very important to ensure that you upgrade them in the environment where you run the program.

Sign Up

Sign In

Forgot Password

ITtutoria Latest Questions

Recommendation for the softmax() got an unexpected keyword argument ‘axis’ error