albumentations-team / autoalbument

AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/
https://albumentations.ai/docs/autoalbument/
MIT License
199 stars 20 forks source link

num_samples=0 error #16

Closed ashish244co closed 3 years ago

ashish244co commented 3 years ago

from e hydra.errors.HydraException: Error calling 'torch.utils.data.DataLoader' : num_samples should be a positive integer value, but got num_samples=0 In my dataset class I am reading things inside a folder where I ran the search command is this the cause ?

ashish244co commented 3 years ago

i print the length of my image path list when dataset.py was instantiated i can see the length is 0 so how can I point working directory to the place where my images are located ?

ashish244co commented 3 years ago

fixed it just had to pass a parameter in root from yaml and then use it

smpurkis commented 3 years ago

Hi @ashish244co, I've encountered the same issue, but am unsure exactly how you fixed it, can you elaborate please? Thanks