Probably it is not a bug for the current models, but I hacked this script locally to run some other models (e.g. state_vggface2_enet0_new.pt). And I wasn't able to run it because of the following error:
Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
Using map_location should help to avoid such problem.
Probably it is not a bug for the current models, but I hacked this script locally to run some other models (e.g. state_vggface2_enet0_new.pt). And I wasn't able to run it because of the following error:
Using
map_locationshould help to avoid such problem.