Model Repository Documentation

Repository Structure Overview

The repository is organized into eight main directories, each serving a specific purpose in the pipeline:

Meta Data (1_meta_data)

Contains AMASS dataset metadata specifically focused on copycat and occlusion information, essential for motion capture applications.

MediaPipe Models (2_mediapipe_ckpts)

Houses MediaPipe's specialized models for facial landmarks and hand tracking, providing fundamental capabilities for human pose estimation.

4DHumans Framework (3_4DHumans)

Incorporates the SMPL (Skinned Multi-Person Linear Model) framework along with training artifacts. The directory includes model parameters, joint regressors, and HMR2 (Human Mesh Recovery) training checkpoints with corresponding configuration files.

SMPLhub (4_SMPLhub)

Serves as a comprehensive collection of human body models, including:

  • MANO (hand model) parameters for both left and right hands
  • SMPL models in various formats (NPZ and PKL) for male, female, and neutral body types
  • SMPLH (SMPL with detailed hand articulation)
  • SMPLX (extended SMPL model with face and hand expressions)

Additional Components

  • S3FD (5_S3FD): Contains face detection model weights
  • SyncNet (6_SyncNet): Includes audio-visual synchronization model
  • SGHM (7_SGHM): Houses ResNet50-based model weights
  • KonIQ (8_koniq): Contains pre-trained weights for image quality assessment
β”œβ”€β”€ 1_meta_data
β”‚   └── amass_copycat_occlusion_v3.pkl
β”œβ”€β”€ 2_mediapipe_ckpts
β”‚   β”œβ”€β”€ face_landmarker.task
β”‚   └── hand_landmarker.task
β”œβ”€β”€ 3_4DHumans
β”‚   β”œβ”€β”€ data
β”‚   β”‚   β”œβ”€β”€ smpl
β”‚   β”‚   β”‚   └── SMPL_NEUTRAL.pkl
β”‚   β”‚   β”œβ”€β”€ smpl_mean_params.npz
β”‚   β”‚   └── SMPL_to_J19.pkl
β”‚   └── logs
β”‚       └── train
β”‚           └── multiruns
β”‚               └── hmr2
β”‚                   └── 0
β”‚                       β”œβ”€β”€ checkpoints
β”‚                       β”‚   └── epoch=35-step=1000000.ckpt
β”‚                       β”œβ”€β”€ dataset_config.yaml
β”‚                       └── model_config.yaml
β”œβ”€β”€ 4_SMPLhub
β”‚   β”œβ”€β”€ 0_misc_files
β”‚   β”‚   └── J_regressor_coco.npy
β”‚   β”œβ”€β”€ MANO
β”‚   β”‚   └── pkl
β”‚   β”‚       β”œβ”€β”€ MANO_LEFT.pkl
β”‚   β”‚       β”œβ”€β”€ mano_mean_params.npz
β”‚   β”‚       └── MANO_RIGHT.pkl
β”‚   β”œβ”€β”€ SMPL
β”‚   β”‚   β”œβ”€β”€ basicmodel_X_lbs_10_207_0_v1.1.0_pkl
β”‚   β”‚   β”‚   β”œβ”€β”€ basicmodel_f_lbs_10_207_0_v1.1.0.pkl
β”‚   β”‚   β”‚   β”œβ”€β”€ basicmodel_m_lbs_10_207_0_v1.1.0.pkl
β”‚   β”‚   β”‚   └── basicmodel_neutral_lbs_10_207_0_v1.1.0.pkl
β”‚   β”‚   β”œβ”€β”€ X_model_npz
β”‚   β”‚   β”‚   β”œβ”€β”€ SMPL_F_model.npz
β”‚   β”‚   β”‚   β”œβ”€β”€ SMPL_M_model.npz
β”‚   β”‚   β”‚   └── SMPL_N_model.npz
β”‚   β”‚   └── X_pkl
β”‚   β”‚       β”œβ”€β”€ SMPL_FEMALE.pkl
β”‚   β”‚       β”œβ”€β”€ SMPL_MALE.pkl
β”‚   β”‚       └── SMPL_NEUTRAL.pkl
β”‚   β”œβ”€β”€ SMPLH
β”‚   β”‚   β”œβ”€β”€ X_npz
β”‚   β”‚   β”‚   β”œβ”€β”€ SMPLH_FEMALE.npz
β”‚   β”‚   β”‚   β”œβ”€β”€ SMPLH_MALE.npz
β”‚   β”‚   β”‚   └── SMPLH_NEUTRAL.npz
β”‚   β”‚   └── X_pkl
β”‚   β”‚       β”œβ”€β”€ SMPLH_female.pkl
β”‚   β”‚       β”œβ”€β”€ SMPLH_male.pkl
β”‚   β”‚       └── SMPLH_NEUTRAL.pkl
β”‚   └── SMPLX
β”‚       β”œβ”€β”€ mod
β”‚       β”‚   └── SMPLX_MALE_shape2019_exp2020.npz
β”‚       └── X_npz
β”‚           β”œβ”€β”€ SMPLX_FEMALE.npz
β”‚           β”œβ”€β”€ SMPLX_MALE.npz
β”‚           └── SMPLX_NEUTRAL.npz
β”œβ”€β”€ 5_S3FD
β”‚   └── sfd_face.pth
β”œβ”€β”€ 6_SyncNet
β”‚   └── syncnet_v2.model
β”œβ”€β”€ 7_SGHM
β”‚   └── SGHM-ResNet50.pth
└── 8_koniq
    └── koniq_pretrained.pkl

Create New Model Repo

Update LFS files

git lfs track "*.gif"
git lfs track "*.jpg"
git lfs track "*.png"

# 4. 使用 git lfs migrate ε‘½δ»€θ½¬ζ’ηŽ°ζœ‰ζ–‡δ»Ά
# θΏ™δΌšε°†ε·²η»ζδΊ€ηš„ζ–‡δ»Άθ½¬ζ’δΈΊ LFS 对豑
git lfs migrate import --include="*.gif,*.jpg,*.png" --everything

# 5. εΌΊεˆΆζŽ¨ι€ζ›΄ζ–°εŽηš„εŽ†ε²
git push --force origin main

Add new repo

git add .
git commit -m "init"
git push
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .