Upload 3 files
Browse files- README (1).md +21 -0
- sfd_face.pth +3 -0
- syncnet_v2.model +3 -0
README (1).md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- syncnet
|
| 4 |
+
- s3fd
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# Model Checkpoints
|
| 8 |
+
|
| 9 |
+
## Pre-trained Models
|
| 10 |
+
|
| 11 |
+
This project includes the following pre-trained model weights:
|
| 12 |
+
|
| 13 |
+
### S3FD Face Detection
|
| 14 |
+
- **Filename**: `sfd_face.pth`
|
| 15 |
+
- **Purpose**: High-accuracy face detection
|
| 16 |
+
- **Architecture**: Single Shot Scale-invariant Face Detector (S3FD)
|
| 17 |
+
|
| 18 |
+
### SyncNet Audio-Visual Synchronization
|
| 19 |
+
- **Filename**: `syncnet_v2.model`
|
| 20 |
+
- **Purpose**: Audio-visual synchronization detection
|
| 21 |
+
- **Original Repo**: https://github.com/joonson/syncnet_python
|
sfd_face.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d54a87c2b7543b64729c9a25eafd188da15fd3f6e02f0ecec76ae1b30d86c491
|
| 3 |
+
size 89844381
|
syncnet_v2.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:961e8696f888fce4f3f3a6c3d5b3267cf5b343100b238e79b2659bff2c605442
|
| 3 |
+
size 54573114
|