map_location argument in torch.load cannot be given as an integer (i.e. 0 must instead be written as 'cuda:0'). See docs. Currently, restoring model using resume_from argument in train.py results in:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/jhultman/.miniconda3/envs/det3d/lib/python3.6/site-packages/torch/serialization.py", line 426, in load
return _load(f, map_location, pickle_module, **pickle_load_args)
File "/home/jhultman/.miniconda3/envs/det3d/lib/python3.6/site-packages/torch/serialization.py", line 613, in _load
result = unpickler.load()
File "/home/jhultman/.miniconda3/envs/det3d/lib/python3.6/site-packages/torch/serialization.py", line 576, in persistent_load
deserialized_objects[root_key] = restore_location(obj, location)
File "/home/jhultman/.miniconda3/envs/det3d/lib/python3.6/site-packages/torch/serialization.py", line 449, in restore_location
result = map_location(storage, location)
TypeError: 'int' object is not callable
map_location
argument intorch.load
cannot be given as an integer (i.e.0
must instead be written as'cuda:0'
). See docs. Currently, restoring model usingresume_from
argument intrain.py
results in: