I’m trying to use mixed precision for transformer vanilla with cpu but i have a problem with the compute of gradient

Pins seem to be involved in the conflict. Currently pinned specs:

My tensorflow graph neural network has a loss function looks like the code below. It calculates the loss based on the input key. Since gnn stores the key in bytes format, and I need to evaluate it to string for hashing the features. But it failed with eager execution is disabled. How to make it works?

Closed 4 days ago.

I am getting error:AttributeError: module ‘tensorflow’ has no attribute ‘get_default_session’
while running stylegan

Let me ask (possibly) a very basic question.
See the code below.

I have followed the tutorial on the TensorFlow Recommenders website and when trying to adapt it to my dataset, the accuracy suddenly becomes extremely low.. like 0.27 for their dataset and 0.0027 for mine.
I have managed at some point to adapt it correctly and have a similar accuracy on my dataset but somehow I ruined the code and now I can’t make it back up.

I try to split string by white spaces and special characters using tf2. tf.strings.split can only split by one delimiter, while tf.strings.regex_replace is very slow. I feel it is very common needs, hence I wonder if there is more generic approach achieve it?

I have been trying all day to install tensorflow with GPU support on a fresh machine with Ubuntu 22.04, but I am struggling heavily to say the least.

As I write ‘import tensorflow as tf’ I get this kinda error message on jupiter notebook. I am new on this platform so i folled many tutorials from youtube. But everytime, the first tensorflow linwe isn’t working.
error_pic