Conv2D(self.filter_1, (1, 64), activation='elu', padding="same",
kernel_constraint=max_norm(2., axis=(0, 1, 2)))(encoder_input)
This is tensoflow code.
What is kernel_constraint=max_norm(2., axis=(0, 1, 2))?
I want to convert this code to pytorch code, but I don’t know how to express the kernel_constraint=max_norm(2., axis=(0, 1, 2)) part. How should I convert it?