Giters

microsoft / RegionCLIP

[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how to train Fully Supervised Object Detection using my own dataset? What is the specific process of training？

ReusJeffery opened this issue · comments

commented

Hello, great job! Could you please tell me how to train Fully Supervised Object Detection using my own dataset? What is the specific process of training?

commented

@ReusJeffery Fully-supervised training is simply the default training of Detectron2, which uses labels of all categories. Please refer to Detectron2 for training on your own dataset. The only major difference is to initialize the model with our pre-trained RegionCLIP.