Hi,

Thanks to share your code.
I run "python main.py --dataset_name screw" and happen below issue.
Could you help me to fix it.
Thank you.

python main.py --dataset_name screw
activation: gelu
b1: 0.5
b2: 0.999
batch_size: 2
data_root: ./datasets/
dataset_name: screw
epoch_num: 150
epoch_start: 0
exp_name: Exp0-r18
factor: 1
image_result_dir: result_images
lr: 0.0001
model_result_dir: saved_models
n_cpu: 1
num_row: 4
seed: 233
unalign_test: False
validation_image_dir: validation_images
device cuda:0
save_dir Exp0-r18-screw/saved_models/checkpoint.pth
train_dataloader <torch.utils.data.dataloader.DataLoader object at 0x0000018D07759820>
test_dataloader <torch.utils.data.dataloader.DataLoader object at 0x0000018D07782EB0>
activation: gelu
b1: 0.5
b2: 0.999
batch_size: 2
data_root: ./datasets/
dataset_name: screw
epoch_num: 150
epoch_start: 0
exp_name: Exp0-r18
factor: 1
image_result_dir: result_images
lr: 0.0001
model_result_dir: saved_models
n_cpu: 1
num_row: 4
seed: 233
unalign_test: False
validation_image_dir: validation_images
device cuda:0
save_dir Exp0-r18-screw/saved_models/checkpoint.pth
train_dataloader <torch.utils.data.dataloader.DataLoader object at 0x000002539E016370>
test_dataloader <torch.utils.data.dataloader.DataLoader object at 0x00000253830CAB20>
Traceback (most recent call last):
File "", line 1, in
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "D:\ProgramData\Anaconda3\envs\env1\lib\runpy.py", line 268, in run_path
return _run_module_code(code, init_globals, run_name,
File "D:\ProgramData\Anaconda3\envs\env1\lib\runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "D:\ProgramData\Anaconda3\envs\env1\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "D:\Code\UTRAD-main\main.py", line 96, in
for i,(filename, batch) in enumerate(train_dataloader):
File "D:\ProgramData\Anaconda3\envs\env1\lib\site-packages\torch\utils\data\dataloader.py", line 359, in iter
return self._get_iterator()
File "D:\ProgramData\Anaconda3\envs\env1\lib\site-packages\torch\utils\data\dataloader.py", line 305, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "D:\ProgramData\Anaconda3\envs\env1\lib\site-packages\torch\utils\data\dataloader.py", line 918, in init
w.start()
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\context.py", line 327, in _Popen
return Popen(process_obj)
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
prep_data = spawn.get_preparation_data(process_obj._name)
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "D:\ProgramData\Anaconda3\envs\env1\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
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.

Hi dear author, thank you for your work! Could you please provide the processed medical-related datasets you mentioned in the paper?

Hi , thanks for that great work & code implementation,

I just have a Question to the training process, For the MVTec dataset: Did you use just 150 epochs to train each model? as statet in the paper, or did you have another metric for the training loop to see when there is a "good" fit? How did you come up with the 150?

Thanks ,
Cheers Pascal