pytorch-deeplab-xception icon indicating copy to clipboard operation
pytorch-deeplab-xception copied to clipboard

hello, a question, can I use my own dataset labeled by labelme to train the model??

Open zhengkai17 opened this issue 6 years ago • 4 comments

hello, a question, can I use my own dataset labeled by labelme to train the model?? thx

zhengkai17 avatar Jul 01 '19 12:07 zhengkai17

yes, you need to change mypath.py and add a class for loading your dataset in 'dataloaders/datasets'. you might also need to add some dataset related functions to 'dataloaders/utils.py'

iariav avatar Jul 02 '19 11:07 iariav

hello, can you specify related functions to train our own models ?

QuanPham99 avatar Aug 21 '19 10:08 QuanPham99

hello, a question, can I use my own dataset labeled by labelme to train the model?? thx

I have the same problem. Have you solved it

kungkook avatar Mar 09 '20 08:03 kungkook

hello,how do you build your dataset file folder?

karryor avatar Aug 15 '20 14:08 karryor