Autoencoder icon indicating copy to clipboard operation
Autoencoder copied to clipboard

pre_model is don't work well

Open zfs1212 opened this issue 6 years ago • 1 comments
trafficstars

Thank your code .However,I want to ask some questions.I have download pre-trained model weights into "models" folder then run: python demo.py .But , have error:RuntimeError :cuda runtime error (10): invalid device ordinal at torch/csrc/cuda/module.cpp:32? I don't know why have error.Can you help me ? Thx.

zfs1212 avatar Jan 04 '19 01:01 zfs1212

This issue maybe you use 4GPUs. I retrain model is work.Thx

zfs1212 avatar Jan 04 '19 03:01 zfs1212