nvalidArgumentError: Computed input depth 384 doesn't match filter input depth 192 [Op:Conv2DBackpropInput]

Hi everyone,

I am currently writing a training loop from scratch using GradientTape and Tensorflow 2.6.0, and I encounter the following error when trying to compute the gradients using tape.gradient().

InvalidArgumentError: Computed input depth 384 doesn’t match filter input depth 192 [Op:Conv2DBackpropInput]

Any ideas how to solve this? I am using two customs loss functions and the model is composed of AlexNet sequential plus several other layers using FunctionalAPI.

Please share standalone code to reproduce the issue reported above? Thank you