search

hitachi-rd-cv / qpic

Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"
Apache License 2.0
131 stars 33 forks source link

How to convert the pretrained DETR model for V-COCO style? #9

Closed weiyunfei closed 3 years ago

weiyunfei commented 3 years ago

Hi! Sorry for bothering again. When I tried to train a V-COCO model, I found that the object classifier of the pre-trained DETR model is only 81-way (including background), while in #6 you claimed that the V-COCO model has an 82-way object classifier (including background and a missing category id). So what should I do to convert the classifier parameters from 81 classes into 82 classes?

tamtamz commented 3 years ago

I fixed the parameter converter for the 82-way object classifier. See the section of the parameter conversion in the README.

weiyunfei commented 3 years ago

Cool! Thanks a lot.