- Made
torch.backend.cudnn.benchmark
option configurable inmonocon_config.py
. (Issue #2)_C.USE_BENCHMARK = True
- Some code has been modified and added to enable video inference using kitti raw dataset.
- A Transform class
Resize3D
for resize augmentation has been added. (Issue #1)
- Visualization functions for 2D Boxes, 3D Boxes, and BEV have been added.
- This repository is released.