Matei Bejan
Matei Bejan
Thanks for reaching back! I've recreated the environment with python 3.8, torch 1.11.0, cuda 10.2 and installed the requirements via pip. However, the error still persists.
I've tested it locally and the problem persists, so it isn't related to Colab's I/O throughput.
Found the source of this behaviour: a code in `/runners/diffusion.py` at line 128: https://github.com/bahjat-kawar/ddrm/blob/73fbbef09a23889401a67ca616aa283a3820d849/runners/diffusion.py#L128. Instead of downloading the class-conditioned conditioned diffusion checkpoint, you download the unconditional one.