search

clovaai / wsolevaluation

Evaluating Weakly Supervised Object Localization Methods Right (CVPR 2020)
MIT License
332 stars 55 forks source link

Dataset Structure #44

Closed ghost closed 3 years ago

ghost commented 3 years ago

Thank you for putting together this brilliant collection of WSOL methods and shedding light on the reality of the progress in the field! Truly appreciated! I was trying to run your code on my own custom dataset following the directions from https://github.com/clovaai/wsolevaluation/issues/17 I was wondering whether the dataset folder hierarchy plays a crucial role in determining class labels. As long as I've correctly produced the class_labels.txt file, do I need to care about the subfolders? For example, I've two labels 0 and 1. Do I need to create two subfolders or putting all the images in one folder should be enough?

junsukchoe commented 3 years ago

Thanks for your interest in our work!

You do not need to care about your dataset structure. You can indicate the class by using csv format. Please see https://github.com/clovaai/wsolevaluation/blob/master/metadata/CUB/train/class_labels.txt for the reference.

ghost commented 3 years ago

Thanks!