Our implementation ofMultiPath++

General Info:

Team behind this solution:

Code Usage:

python3 prerender/prerender.py \    --data-path /path/to/original/data \    --output-path /output/path/to/prerendered/data \    --n-jobs 24 \    --n-shards 1 \    --shard-id 0 \    --config configs/prerender.yaml

python3 train.py configs/final_RoP_Cov_Single.yaml

Citation

@misc{https://doi.org/10.48550/arxiv.2206.10041,  doi = {10.48550/ARXIV.2206.10041},  url = {https://arxiv.org/abs/2206.10041},  author = {Konev, Stepan},  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},  title = {MPA: MultiPath++ Based Architecture for Motion Prediction},  publisher = {arXiv},  year = {2022},  copyright = {arXiv.org perpetual, non-exclusive license}}