HoP
HoP copied to clipboard
[ICCV 2023] Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction
hi ,can you share with me the bevformer+hop config? many thanks! email : [[email protected]](mailto:[email protected])
Hi, @TempleX98 @Sense-X @CaraJ7 Thanks for your great work! I'd like to know any plan to release code for HoP on BEVFormer?
Hi, I'm looking for the model that is on the nuScenes detection leaderboard. Will you be posting it in the model Zoo? Or is it the same as one of...
Hello, I am trying to prepare my dataset by typing the cmd: python tools/create_data.py --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes as suggested in the tutorial but i get this error:...
hi. i got on error, but i have no idea to fix it. Traceback (most recent call last): File "tools/train.py", line 288, in main() File "tools/train.py", line 277, in main...
(1) I used mmcv.imread to read the data, because directly using mmcv.load as in your code would result in an error, indicating unsupported `color`. (2) Using the configuration hop_bevdet4d-r50-depth.py and...
The paper claims that "Accordingly, we first employ a channel reduction operation to the input set Brem to prune the height information and achieve better training efficiency". But why channel...
Hi, I am wondering do you compare the results of the reconstructed bev feature with the real bev feature at timestamp t-k?