ZFTurbo / Weighted-Boxes-Fusion

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.
MIT License
1.7k stars 237 forks source link

weighted boxes fusion on single model #28

Open SISTMrL opened 3 years ago

SISTMrL commented 3 years ago

hello, today i found a repo: https://github.com/kentaroy47/ODA-Object-Detection-ttA this repo also use the wbf, you can find the code in adach/oda.py/line 192 class TTAWrapper. you can see the example.ipynb in that repo, i found oda use the wbf just only one model. I remember that you say that wbf on single model, the performance will drop. how do i choose the nms option in class TTAWrapper in oda? just nms='nms' not nms='wbf', thanks?

ZFTurbo commented 3 years ago

WBF works great for TTA. It's bad for filtering boxes from single model. TTA != Single model

SISTMrL commented 3 years ago

i saw that repo use single model, how can i use multiple models in that repo