the test model looks like based on cuda device

[hi589dsTq92]

Hi bor:
when I try to run test.py, and when the code go into line 58:
trainer.load_checkpoint(log_dir + 'checkpoint')
then an error happend at here.
'''
raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: 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.
'''
this looks like means I must run these code on a cuda device.
or because of this test model is trained on a cuda device, I must build a new model which supported on CPU only?

[Xu-Yao]

Hello knowasdf, I tried to reproduce the issue but did not succeed. I searched your question and find this. So I propose to replace the line 219 of trainer.py by
"""
state_dict = torch.load(checkpoint_path, map_location={'cuda:0': 'cpu'})
"""
I hope that could help you solve the problem :)

[hi589dsTq92]

Hey bro:
cool job!! it's WORKING now.
for adaptability, I revised some code like these:
trainer.py at line 218,219:
def load_checkpoint(self, checkpoint_path, device={'cuda:0': 'cpu'}):
state_dict = torch.load(checkpoint_path, device)
train.py at line 77:
epoch_0 = trainer.load_checkpoint(opts.checkpoint, device)
test.py at line 56:
trainer.load_checkpoint(opts.checkpoint, device)
test.py at line 58:
trainer.load_checkpoint(log_dir + 'checkpoint', device)

;)