-
UPDATE❗ Related repo with 3rd place solution code for Waymo Motion Prediction Challenge 2022
-
UPDATE❗ Related repo with refactored code for MotionCNN
- Artsiom Sanakoyeu [Homepage] [Twitter] [Telegram Channel] [LinkedIn]
- Stepan Konev [LinkedIn]
- Kirill Brodt [GitHub]
Download
datasets
uncompressed/tf_example/{training,validation,testing}
Change paths to input dataset and output folders
python prerender.py \
--data /home/data/waymo/training \
--out ./train
python prerender.py \
--data /home/data/waymo/validation \
--out ./dev \
--use-vectorize \
--n-shards 1
python prerender.py \
--data /home/data/waymo/testing \
--out ./test \
--use-vectorize \
--n-shards 1MODEL_NAME=xception71
python train.py \
--train-data ./train \
--dev-data ./dev \
--save ./${MODEL_NAME} \
--model ${MODEL_NAME} \
--img-res 224 \
--in-channels 25 \
--time-limit 80 \
--n-traj 6 \
--lr 0.001 \
--batch-size 48 \
--n-epochs 120python submit.py \
--test-data ./test/ \
--model-path ${MODEL_PATH_TO_JIT} \
--save ${SAVE}python visualize.py \
--model ${MODEL_PATH_TO_JIT} \
--data ${DATA_PATH} \
--save ./vizIf you find our work useful, please cite it as:
@misc{konev2022motioncnn,
title={MotionCNN: A Strong Baseline for Motion Prediction in Autonomous Driving},
author={Stepan Konev and Kirill Brodt and Artsiom Sanakoyeu},
year={2022},
eprint={2206.02163},
archivePrefix={arXiv},
primaryClass={cs.CV}
}