lithiumice
commited on
Commit
Β·
04ade0a
1
Parent(s):
e7fcdee
add readme
Browse files
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model Repository Documentation
|
2 |
+
|
3 |
+
## Repository Structure Overview
|
4 |
+
|
5 |
+
The repository is organized into eight main directories, each serving a specific purpose in the pipeline:
|
6 |
+
|
7 |
+
### Meta Data (1_meta_data)
|
8 |
+
Contains AMASS dataset metadata specifically focused on copycat and occlusion information, essential for motion capture applications.
|
9 |
+
|
10 |
+
### MediaPipe Models (2_mediapipe_ckpts)
|
11 |
+
Houses MediaPipe's specialized models for facial landmarks and hand tracking, providing fundamental capabilities for human pose estimation.
|
12 |
+
|
13 |
+
### 4DHumans Framework (3_4DHumans)
|
14 |
+
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.
|
15 |
+
|
16 |
+
### SMPLhub (4_SMPLhub)
|
17 |
+
Serves as a comprehensive collection of human body models, including:
|
18 |
+
- MANO (hand model) parameters for both left and right hands
|
19 |
+
- SMPL models in various formats (NPZ and PKL) for male, female, and neutral body types
|
20 |
+
- SMPLH (SMPL with detailed hand articulation)
|
21 |
+
- SMPLX (extended SMPL model with face and hand expressions)
|
22 |
+
|
23 |
+
### Additional Components
|
24 |
+
- S3FD (5_S3FD): Contains face detection model weights
|
25 |
+
- SyncNet (6_SyncNet): Includes audio-visual synchronization model
|
26 |
+
- SGHM (7_SGHM): Houses ResNet50-based model weights
|
27 |
+
- KonIQ (8_koniq): Contains pre-trained weights for image quality assessment
|
28 |
+
|
29 |
+
```
|
30 |
+
βββ 1_meta_data
|
31 |
+
β βββ amass_copycat_occlusion_v3.pkl
|
32 |
+
βββ 2_mediapipe_ckpts
|
33 |
+
β βββ face_landmarker.task
|
34 |
+
β βββ hand_landmarker.task
|
35 |
+
βββ 3_4DHumans
|
36 |
+
β βββ data
|
37 |
+
β β βββ smpl
|
38 |
+
β β β βββ SMPL_NEUTRAL.pkl
|
39 |
+
β β βββ smpl_mean_params.npz
|
40 |
+
β β βββ SMPL_to_J19.pkl
|
41 |
+
β βββ logs
|
42 |
+
β βββ train
|
43 |
+
β βββ multiruns
|
44 |
+
β βββ hmr2
|
45 |
+
β βββ 0
|
46 |
+
β βββ checkpoints
|
47 |
+
β β βββ epoch=35-step=1000000.ckpt
|
48 |
+
β βββ dataset_config.yaml
|
49 |
+
β βββ model_config.yaml
|
50 |
+
βββ 4_SMPLhub
|
51 |
+
β βββ 0_misc_files
|
52 |
+
β β βββ J_regressor_coco.npy
|
53 |
+
β βββ MANO
|
54 |
+
β β βββ pkl
|
55 |
+
β β βββ MANO_LEFT.pkl
|
56 |
+
β β βββ mano_mean_params.npz
|
57 |
+
β β βββ MANO_RIGHT.pkl
|
58 |
+
β βββ SMPL
|
59 |
+
β β βββ basicmodel_X_lbs_10_207_0_v1.1.0_pkl
|
60 |
+
β β β βββ basicmodel_f_lbs_10_207_0_v1.1.0.pkl
|
61 |
+
β β β βββ basicmodel_m_lbs_10_207_0_v1.1.0.pkl
|
62 |
+
β β β βββ basicmodel_neutral_lbs_10_207_0_v1.1.0.pkl
|
63 |
+
β β βββ X_model_npz
|
64 |
+
β β β βββ SMPL_F_model.npz
|
65 |
+
β β β βββ SMPL_M_model.npz
|
66 |
+
β β β βββ SMPL_N_model.npz
|
67 |
+
β β βββ X_pkl
|
68 |
+
β β βββ SMPL_FEMALE.pkl
|
69 |
+
β β βββ SMPL_MALE.pkl
|
70 |
+
β β βββ SMPL_NEUTRAL.pkl
|
71 |
+
β βββ SMPLH
|
72 |
+
β β βββ X_npz
|
73 |
+
β β β βββ SMPLH_FEMALE.npz
|
74 |
+
β β β βββ SMPLH_MALE.npz
|
75 |
+
β β β βββ SMPLH_NEUTRAL.npz
|
76 |
+
β β βββ X_pkl
|
77 |
+
β β βββ SMPLH_female.pkl
|
78 |
+
β β βββ SMPLH_male.pkl
|
79 |
+
β β βββ SMPLH_NEUTRAL.pkl
|
80 |
+
β βββ SMPLX
|
81 |
+
β βββ mod
|
82 |
+
β β βββ SMPLX_MALE_shape2019_exp2020.npz
|
83 |
+
β βββ X_npz
|
84 |
+
β βββ SMPLX_FEMALE.npz
|
85 |
+
β βββ SMPLX_MALE.npz
|
86 |
+
β βββ SMPLX_NEUTRAL.npz
|
87 |
+
βββ 5_S3FD
|
88 |
+
β βββ sfd_face.pth
|
89 |
+
βββ 6_SyncNet
|
90 |
+
β βββ syncnet_v2.model
|
91 |
+
βββ 7_SGHM
|
92 |
+
β βββ SGHM-ResNet50.pth
|
93 |
+
βββ 8_koniq
|
94 |
+
βββ koniq_pretrained.pkl
|
95 |
+
```
|