module 'tensorflow' has no attribute 'log'

12,256

Solution 1

loss = tf.keras.losses.categorical_crossentropy

I also faced a similar issue then i called tensorflow with each Keras object and it resolved it

Solution 2

substitute tf.math.log for tf.log in tf 2.0.

Solution 3

If you know the exact line where tf.log is, replace it with tf.math.log.
if not, you can use this guide to Automatically upgrade code to TensorFlow 2

Share:
12,256

Related videos on Youtube

neelima golla
Author by

neelima golla

Updated on June 04, 2022

Comments

  • neelima golla
    neelima golla almost 2 years
    fashion_model.compile(
        loss = keras.losses.categorical_crossentropy,
        optimizer = tf.keras.optimizers.Adam(),
        metrics = ['accuracy']
    )
    

    When I execute this line of code I am facing the error

    module 'tensorflow' has no attribute 'log'

    and my tensorflow version is 2.0

    • Akash Basudevan
      Akash Basudevan over 4 years
      Can you post the complete code?