Jiazhi Yang
Jiazhi Yang
I run the occupancy_and_flow_tutorial directly and submit the generated submission to the server (Validation server, not the Test one). However, it seems that the server is not working(stuck more than...
 You only reported detection results based on V2-99 backbone, but I was wondering the results on res101 to make a comparision between PETRV2 and BEVFormer.
As far as I know, deformable conv also learns the shape or apperance of an object and has been proven effective in various vision tasks. I'm not sure about the...
I'm confused about the implementation of fusing features from two branches. In the combiner.py of your code, it seems that features from two branchs are mixed by concatenating. (Related codes...
https://github.com/ShoufaChen/DiffusionDet/blob/1efb36d4b0b721f2d509bc72656235a94d73ab02/diffusiondet/detector.py#L400-L403 Though you clamped the coordinates (x) at line400, they may become negative number when converted from (cx, cy, w, h) to (x, y, x, y) mode. Here is an...
We will continually collect frequently asked questions and good questions in this thread. ## Frequently Asked Questions ## Good Questions 1. What do we think of the open-loop evaluation? Are...
We will continually gather both frequently asked- and good questions in this thread. ## Frequently Asked Questions 1. Unexpected key when loading stage2 model? https://github.com/OpenDriveLab/UniAD/issues/97 **Answer**: `unexpected key in source...