Tensorflow v2.16 tf.keras.layers Embedding not accepting argument for input_length

Question

While working with Embedding for an LSTM model I came across an issue with input_length:

ValueError: Unrecognized keyword arguments passed to Embedding: {'input_length': 536}

Is input length being replaced with something else? Is this an error with the early release version or is the argument for the Embedding layer getting updated? How can I specify the input_length in the embedding layer for keras from tf 2.16?

It seems like python 3.12 does not have any other available tensorflow versions available, when trying to do pip install tensorflow=2.15.0 or any other version I get an error saying that pip can't find it. Should I adjust the python version on my machine or get Anaconda navigator to adjust it? Does it make it easy to work with different python version?

I tired installing another version of tensorflow to fix it but no other versions are available for python 3.12.

Please provide enough code so others can better understand or reproduce the problem. — Community
– Community Bot, Commented Feb 27, 2024 at 22:06
I see the same issue with tensorflow 2.15.0 with the following code: ``` import tensorflow as tf model = tf.keras.models.Sequential() model.add(tf.keras.layers.Embedding(24, 10, input_length=4)) ``` — mhsnk
– mhsnk, Commented Mar 4, 2024 at 1:02

Hamed Rezaee · Accepted Answer · 2024-03-05 21:10:48Z

1

replace input_length with input_shape.

edited Mar 5, 2024 at 21:10

Hamed Rezaee

7,2986 gold badges44 silver badges63 bronze badges

answered Mar 4, 2024 at 10:35

Mobin

112 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Tensorflow v2.16 tf.keras.layers Embedding not accepting argument for input_length

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related