Skip to content

pretrained model for GAC
Compare
Choose a tag to compare
@Owen-Liuyuxuan Owen-Liuyuxuan released this 01 Feb 08:16
· 18 commits to master since this release
1.0
3affa28

Pretrained model for Ground-aware Monocular 3D Object Detection for Autonomous Driving.

the model file could be placed under workdirs/Yolo3D/checkpoint/ (you should provide the path to the model file in the command line)

anchor_mean/std_Car.npy should be placed under workdirs/Yolo3D/output/training. You can reproduce the npy file with the scripts runned on the 'test split'.

Benchmark Easy Moderate Hard
Car Detection 92.35 % 79.57 % 59.61 %
Car Orientation 90.87 % 77.47 % 57.99 %
Car 3D Detection 21.60 % 13.17 % 9.94 %
Car Bird's Eye View 29.38 % 18.00 % 13.14 %
Assets 6