xwjabc / hed

A PyTorch reimplementation of Holistically-Nested Edge Detection

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About the datasets

long123524 opened this issue · comments

commented

What should the composition of the data set folder look like? What does the .lst file do? Beginners ask for advice

You can refer to https://github.com/xwjabc/hed/blob/master/datasets.py#L19
Basically, in train_pair.lst, each line has an image path and its corresponding edge path.
In test.lst, each line has an image path.
The dataset folder structure can be arbitrary as long as the .lst files follow the above description.