Wednesday, January 18, 2023

Tensorflow 1.x to 2.x

I changed the only function from Tensorflow 1.x of TempoGAN that I mentioned in this post, from

tf.contrib.layers.batch_norm()

to

tf.compat.v1.layers.batch_normalization()

and, of course, the pre-trained weights are useless now that I changed the net structure. So, I need to retrain it, but there is no script to do it. I can do one myself and be very careful when choosing the parameters. Or, I use Google Colab to run the original net for me.

You may have noticed that Google Colab does not support Tensorflow 1.x anymore, right? But no worries. I've found a way to overcome this with miniconda here.

No comments:

Post a Comment

Global Game Jam 2024

Wow, what a weekend. The Global Game Jam is intense. But I and 3 other members manage to build a game for the theme "Make me laugh&quo...