You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello,your great job is amazing!I have tried to train MapTRv2. When training without a centerline version, it is normal. I obtained results similar to your paper. However, when I tried the centerline version, it seems to have some problems, that the mAP of centerline is still zero. Just like the following figures:
And it seems that the gts of centerline is none. Is it a problem I encountered while generating data? I used "python tools/maptrv2/custom_nusc_map_converter.py --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes --version v1.0 --canbus ./data " to generate the annotations.
The text was updated successfully, but these errors were encountered:
Hello,your great job is amazing!I have tried to train MapTRv2. When training without a centerline version, it is normal. I obtained results similar to your paper. However, when I tried the centerline version, it seems to have some problems, that the mAP of centerline is still zero. Just like the following figures:
And it seems that the gts of centerline is none. Is it a problem I encountered while generating data? I used "python tools/maptrv2/custom_nusc_map_converter.py --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes --version v1.0 --canbus ./data " to generate the annotations.
The text was updated successfully, but these errors were encountered: