Kemal Oksuz
Kemal Oksuz
Thanks for the nice work. I checked GFLv2 paper, this repo and config files, but I could not find which scales you used to obtain 53.3 AP on R2-101-DCN backbone....
This is the implementation of LRP Error on open-mmlab COCOapi. In the output file, in addition to the standard AP-based values, you will see LRP Error, components and class-wise optimal...
If so, when are you planning to release? Thanks
Congratulations for the great works and thanks for sharing the code. In order to make VADv2 work, carla_plan_vocabulary_4096.npy is needed. Could you please share this file or a script to...