nyuuzyou
commited on
Commit
•
b833105
1
Parent(s):
b7d1ead
Initial commit - adding the three versions of the anime object detection models
Browse files- README.md +47 -3
- examples/1v1.jpg +0 -0
- examples/1v2.jpg +0 -0
- examples/1v3.jpg +0 -0
- examples/2v1.jpg +0 -0
- examples/2v2.jpg +0 -0
- examples/2v3.jpg +0 -0
- examples/3v1.jpg +0 -0
- examples/3v2.jpg +0 -0
- examples/3v3.jpg +0 -0
- weights/animeheads.pt +3 -0
- weights/animeheadsv2.pt +3 -0
- weights/animeheadsv3.pt +3 -0
README.md
CHANGED
@@ -1,3 +1,47 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Anime Head Detection Models
|
2 |
+
|
3 |
+
This repository contains three object detection models based on YOLOv5l and YOLOv8l architectures. The images in the dataset were taken from anime and art, with manga pages added to AnimeHeadsv3.
|
4 |
+
|
5 |
+
## Versions
|
6 |
+
|
7 |
+
### AnimeHeadsv3
|
8 |
+
|
9 |
+
- Description: The third and last version of the project based on YOLOv8l. The training set contains 8037 images.
|
10 |
+
- Augmentation parameters:
|
11 |
+
- Outputs per training example: 3
|
12 |
+
- Flip: Horizontal
|
13 |
+
- Saturation: Between -40% and +40%
|
14 |
+
- Blur: Up to 4px
|
15 |
+
- Noise: Up to 4% of pixels
|
16 |
+
- Example images:
|
17 |
+
|
18 |
+
![Example image 1](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/1v3.jpg)
|
19 |
+
![Example image 2](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/2v3.jpg)
|
20 |
+
![Example image 3](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/3v3.jpg)
|
21 |
+
|
22 |
+
- Model file: `animeheadsv3.weight`
|
23 |
+
|
24 |
+
### AnimeHeadsv2
|
25 |
+
|
26 |
+
- Description: The second version of the project based on YOLOv8l. The training set contains 4632 images.
|
27 |
+
- Augmentation parameters:
|
28 |
+
- Outputs per training example: 3
|
29 |
+
- Blur: Up to 2.75px
|
30 |
+
- Noise: Up to 5% of pixels
|
31 |
+
- Example images:
|
32 |
+
|
33 |
+
![Example image 1](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/1v2.jpg)
|
34 |
+
![Example image 2](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/2v2.jpg)
|
35 |
+
![Example image 3](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/3v2.jpg)
|
36 |
+
- Model file: `animeheadsv2.weight`
|
37 |
+
|
38 |
+
### AnimeHeads
|
39 |
+
|
40 |
+
- Description: The first version of the project based on YOLOv5l. The training set contains 886 images.
|
41 |
+
- Augmentation parameters: None
|
42 |
+
- Example images:
|
43 |
+
|
44 |
+
![Example image 1](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/1v1.jpg)
|
45 |
+
![Example image 2](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/2v1.jpg)
|
46 |
+
![Example image 3](https://huggingface.co/nyuuzyou/AnimeHeads/resolve/main/examples/3v1.jpg)
|
47 |
+
- Model file: `animeheads.weight`
|
examples/1v1.jpg
ADDED
examples/1v2.jpg
ADDED
examples/1v3.jpg
ADDED
examples/2v1.jpg
ADDED
examples/2v2.jpg
ADDED
examples/2v3.jpg
ADDED
examples/3v1.jpg
ADDED
examples/3v2.jpg
ADDED
examples/3v3.jpg
ADDED
weights/animeheads.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95af17f4005c49eb1e906d7fb92e49a288917703a8e4bf4198ca6e98be7ed7b9
|
3 |
+
size 14441405
|
weights/animeheadsv2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcfbeff256a6cc2ced0e8bd20c5ef525717d99e3bc748ce63fb742b3dea82a98
|
3 |
+
size 87620552
|
weights/animeheadsv3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22e1500fc5a4b7f3c46f3ef8ff89b50b6aed542ecccbd7c2bd0d86c70f773a35
|
3 |
+
size 87621064
|