Skip to content

Latest commit

 

History

History
61 lines (40 loc) · 1.51 KB

mesh.md

File metadata and controls

61 lines (40 loc) · 1.51 KB

Human Mesh Recovery

Data

  1. Download the datasets here and put them to data/mesh/. We use Human3.6M, COCO, and PW3D for training and testing. Descriptions of the joint regressors could be found in SPIN.
  2. Download the SMPL model(basicModel_neutral_lbs_10_207_0_v1.0.0.pkl) from SMPLify, put it to data/mesh/, and rename it as SMPL_NEUTRAL.pkl

Running

Train from scratch:

# with 3DPW
python train_mesh.py \
--config configs/mesh/MB_train_pw3d.yaml \
--checkpoint checkpoint/mesh/MB_train_pw3d

# H36M
python train_mesh.py \
--config configs/mesh/MB_train_h36m.yaml \
--checkpoint checkpoint/mesh/MB_train_h36m

Finetune from a pretrained model:

# with 3DPW
python train_mesh.py \
--config configs/mesh/MB_ft_pw3d.yaml \
--pretrained checkpoint/pretrain/MB_release \
--checkpoint checkpoint/mesh/FT_MB_release_MB_ft_pw3d

# H36M
python train_mesh.py \
--config configs/mesh/MB_ft_h36m.yaml \
--pretrained checkpoint/pretrain/MB_release \
--checkpoint checkpoint/mesh/FT_MB_release_MB_ft_h36m

Evaluate:

# with 3DPW
python train_mesh.py \
--config configs/mesh/MB_train_pw3d.yaml \
--evaluate checkpoint/mesh/MB_train_pw3d/best_epoch.bin 

# H36M
python train_mesh.py \
--config configs/mesh/MB_train_h36m.yaml \
--evaluate checkpoint/mesh/MB_train_h36m/best_epoch.bin