Specific use of cuda model not allowing cpu compute

[rg314]

this line of code (line 71 of pipeline_cnn.py as of commit 6f1968a):
best_model = torch.hub.load_state_dict_from_url('https://docs.google.com/uc?export=download&id=13CLZoNyvCt2K46UvAyHUqH7099FbnBh_')

errors on _cuda_deserialize.

Assuming that this model specifically is cuda-based and therefore cannot be deserialised for cpu computation.

Should the model be ensured to work across both CUDA and CPU compute?

Same issue from @Phlair raised in autoballs

[Phlair]

see:
rg314/autoballs#7

[rg314]

Needs to include map_location to point at current device

import torch
best_model = torch.hub.load_state_dict_from_url(
'https://docs.google.com/uc?export=download&id=13CLZoNyvCt2K46UvAyHUqH7099FbnBh_', 
map_location='cpu')