pytorch error when loading data:
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
{X = dataloaders: torch.utils.data.DataLoader (image_datasets [X], the batch_size = opt.batchsize,
shuffle = False, num_workers = 0) in X for
reasons: the need to run multiple processes in the main function,
Solution 1:
Plus main function call in main
Solution 2:
num_workers to 0, the process of loading a single