Detectron: How to train the custom dataset.
Hi! First, thank you for your wonderful works.
I finish training the RetinaNet with COCO dataset as you instructed.
I want to train my own dataset with RetinaNet or another baseline models.
I look at the inside code structure and figure out that all model configurations are defined in *.yaml file and train_net.py read the *.yaml file and construct the database from .jason file in COCO annotations directory.
So if I want to train my own dataset, the only way is to generate the .json file similar with COCO annotations?
nonstop1962
All 5 comments
@nonstop1962: yes, the recommended way is to convert your dataset to the COCO json annotation format. For bounding boxes, this can usually be done in < 100 lines of Pythons. Of course you could make arbitrary modification to the Detectron code to support custom formats, but that's probably harder and more prone to issues with missed corner cases.
rbgirshick
on 25 Jan 2018
Thank you for your answer!
nonstop1962
on 25 Jan 2018
Thank you for @rbgirshick !
Ok, so Can I get training dataset if I want to segment T-Shirt ?
for example, JSON get for uses of COCO API.
I think that this platform can segmentation.
ok??
Thank you~!
oryondark
on 19 Sep 2018
Hi,
for those who need it, here's a script for converting xml pascal voc annotations to coco json format : https://github.com/gamcoh/Object-Detection-Tools/blob/master/pascal_voc_xml2coco_json.py
gamcoh
on 20 Mar 2019
Thank gamcoh
oryondark
on 21 Mar 2019
Related issues
baristahell
·
3Comments
partnercloudsupport
·
3Comments
Hwang-dae-won
·
3Comments
fangpengcheng95
·
4Comments
gaopeng-eugene
·
4Comments
Most helpful comment
@nonstop1962: yes, the recommended way is to convert your dataset to the COCO json annotation format. For bounding boxes, this can usually be done in < 100 lines of Pythons. Of course you could make arbitrary modification to the Detectron code to support custom formats, but that's probably harder and more prone to issues with missed corner cases.