rosasalberto / StyleGAN2-TensorFlow-2.x

Unofficial implementation of StyleGAN2 using TensorFlow 2.x.
143 stars 40 forks source link

Deeper explanation #11

Open Gresliebear opened 3 years ago

Gresliebear commented 3 years ago

The Conv2D op currently does not support grouped convolutions on the CPU. In consequence, when running with CPU, batch size should be 1.

Why does CPU not support Conv2D? I was just curious for deeper technical explanation.

kinda of fixed? https://github.com/tensorflow/tensorflow/commit/7b8db6083b34520688dbc71f341f7aeaf156bf17