[ICCV 2021] Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation

pip install -r requirements.txt

python -u -m torch.distributed.launch \
    --nnodes=2 \
    --node_rank=0 \
    --nproc_per_node=4 \
    --master_port=<MASTER_PORT> \
    --master_addr=<MASTER_NODE_ID> \
    --use_env \
    train.py --cfg configs/config_stage1.yaml

python -u -m torch.distributed.launch \
    --nnodes=2 \
    --node_rank=1 \
    --nproc_per_node=4 \
    --master_port=<MASTER_PORT> \
    --master_addr=<MASTER_NODE_ID> \
    --use_env \
    train.py --cfg configs/config_stage1.yaml

# training on 2 nodes, 4 gpus each (2x4=8 gpus total)
sh scripts/run.sh 2 4 configs/config_stage1.yaml

# On Node 0.
python -u -m torch.distributed.launch \
    --nnodes=2 \
    --node_rank=0 \
    --nproc_per_node=4 \
    --master_port=<MASTER_PORT> \
    --master_addr=<MASTER_NODE_ID> \
    --use_env \
    train.py --cfg configs/config_stage2.yaml --pretrained <PATH_TO_CHECKPOINT_FILE>

python eval.py --cfg <PATH_TO_EXPERIMENT>/config.yaml --checkpoint <PATH_TO_EXPERIMENT>/model_best.pth.tar --eval_set 3dpw

@inproceedings{wan2021,
  title={Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation},
  author={Ziniu Wan, Zhengjia Li, Maoqing Tian, Jianbo Liu, Shuai Yi, Hongsheng Li},
  booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
  year = {2021}
}