Have you used tf.keras in TensorFlow 2.0 recently? We'd like your feedback. Here's a 15-second survey:https://forms.gle/cpBgkAF623rhpW3D9 …
Show this thread
-
I ran into a weird problem. When implementing 2DCNN for GAN, no gradients flown back if using tf.function decorator + tf while loops. tf.function + python loops = fine, or tf while loops without using tf.function is also fine. And the problem disappears when upgrading to tf 2.1
