search

WXinlong / SOLO

SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
Other
1.71k stars 307 forks source link

How to test after one epoch？ #226

Closed songyangsun closed 2 years ago

songyangsun commented 2 years ago

now,only test at last. How to test after one epoch？

HuygheB commented 2 years ago

@songyangsun have you found a method to do it?

hiiro0420 commented 2 years ago

if you use configs/solo/solo_r50_fpn_8gpu_1x.py, you change "workflow = [('train',1),('val',1)]" in configs/solo/solo_r50_fpn_8gpu_1x.py.

hiiro0420 commented 2 years ago

https://mmcv.readthedocs.io/en/latest/understand_mmcv/runner.html#epochbasedrunner is very useful

songyangsun commented 2 years ago

i try it

songyangsun commented 2 years ago

if you use configs/solo/solo_r50_fpn_8gpu_1x.py, you change "workflow = [('train',1),('val',1)]" in configs/solo/solo_r50_fpn_8gpu_1x.py.

I try it,but it can't do eval in SOLO. Can you do eval and print mAP result?

songyangsun commented 2 years ago

if you use configs/solo/solo_r50_fpn_8gpu_1x.py, you change "workflow = [('train',1),('val',1)]" in configs/solo/solo_r50_fpn_8gpu_1x.py.

I try it,but it can't do eval in SOLO. Can you do eval and print mAP result?

I use mmdetection to solve it,please refer to it.