Get error when Create black and white training images

[Tom797]

I try to use ColorizeTrainingStable.ipynb to train a model, When I run to

if not path_lr.exists(): il = ImageList.from_folder(path_hr) parallel(create_training_images, il.items)

i get following warning

BrokenProcessPool Traceback (most recent call last) Cell In[10], line 3 1 if not path_lr.exists(): 2 il = ImageList.from_folder(path_hr) ----> 3 parallel(create_training_images, il.items)

File F:\image\project\DeOldify-ImageColorizer\fastai\core.py:355, in parallel(func, arr, max_workers, leave) 353 results = [] 354 for f in progress_bar(concurrent.futures.as_completed(futures), total=len(arr), leave=leave): --> 355 results.append(f.result()) 356 if any([o is not None for o in results]): return results

File F:\Anaconda\envs\deoldify\lib\concurrent\futures_base.py:451, in Future.result(self, timeout) 449 raise CancelledError() 450 elif self._state == FINISHED: --> 451 return self.__get_result() 453 self._condition.wait(timeout) 455 if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:

File F:\Anaconda\envs\deoldify\lib\concurrent\futures_base.py:403, in Future.__get_result(self) 401 if self._exception: 402 try: --> 403 raise self._exception 404 finally: 405 # Break a reference cycle with the exception in self._exception 406 self = None

BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.

and my floder not create the "data/imagenet/ILSVRC/Data/CLS-LOC/bandw" , how should I do?

[Tom797]

Change the code to

if not path_lr.exists(): il = ImageList.from_folder(path_hr) for i in range(len(il.items)): create_training_images(il.items[i],1) print(il.items)

can solve problems