[FIXED] Suppression of Tensorflow Warning

Issue

I have a tensorflow 2.x functional model model whose first layers are from another pretrained model. I want those layers to remain frozen, so I have used tf.stop_gradient on the pretrained head to stop them from learning. Below is a minimal example of my network:

head =  load_my_cool_pretrained_representation_model()
x = tf.keras.layers.Dense(10000)(tf.stop_gradient(head.output))
x = tf.keras.layers.Dense(1)(x)
model = tf.keras.Model(inputs=head.inputs, outputs=x)
model.compile(loss='mse', optimizer=tf.keras.optimizers.Adam())

When I use model.fit() I get the following warning:

WARNING:tensorflow:Gradients do not exist for variables ['cool_rep_layer/embeddings:0', ...] when minimizing the loss.

I do not need the warning as I want those layers to not have gradients. How can I suppress this warning? I have looked at this answer, but I do not want to get into gradient tape for this model.

Solution

As per noober's comment, I just added

import logging
logging.getLogger('tensorflow').setLevel(logging.ERROR)

to get rid of the warnings. This worked for me.

Answered By - Ottpocket