-
Notifications
You must be signed in to change notification settings - Fork 60
dataloading issue #11
Comments
you can modify the path in metadata.json |
Thank you! That has worked. However I am getting another error now. Can't understand what this means... (siamese_nested_unet) PS G:\NeuroPixel\segmentation\unet_plus_plus\siamese_nested_unet\Siam-NestedUNet-master> python train.py
prepare(preparation_data) File "train.py", line 79, in
for batch_img1, batch_img2, labels in tbar: File "F:\Anaconda\envs\siamese_nested_unet\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path File "F:\Anaconda\envs\siamese_nested_unet\lib\site-packages\torch\utils\data\dataloader.py", line 359, in iter
return _MultiProcessingDataLoaderIter(self) File "F:\Anaconda\envs\siamese_nested_unet\lib\multiprocessing\context.py", line 223, in _Popen File "F:\Anaconda\envs\siamese_nested_unet\lib\multiprocessing\context.py", line 322, in _Popen
BrokenPipeError: [Errno 32] Broken pipe |
Reduce the num of workers when you load the dataset. |
Even when reducing the number of workers to 1, a freeze_support() error is being displayed:
|
Hi! Thanks for uploading the code. I am facing the above error when running : "python train.py"
Looks like there is something wrong with the folder structure maintained by me or may be I need to provide the folder structure path as input somewhere. Can you kindly shed light on how to resolve this issue?
The text was updated successfully, but these errors were encountered: