NSFW-API commited on
Commit
8181995
·
verified ·
1 Parent(s): 8c461d5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -8
README.md CHANGED
@@ -1,15 +1,18 @@
1
  # NSFW Segmentation
2
 
3
- Multi-head release of three single-task segmentation models targeting NSFW anatomy. Each checkpoint runs independently and produces binary masks for the specified classes.
4
 
5
- | File | Task | Classes | Mask mAP@0.5 | Mask mAP@0.5:0.95 |
6
- | --- | --- | --- | --- | --- |
7
- | `nsfw-seg-breast.pt` | Breast anatomy | breast, areola, nipple | 0.895 | 0.636 |
8
- | `nsfw-seg-vagina.pt` | Vagina | vagina | 0.995 | 0.871 |
9
- | `nsfw-seg-penis.pt` | Penis | penis | 0.995 | 0.975 |
 
 
 
10
 
11
  ## Description
12
- - Backbone: YOLO11s segmentation head (Ultralytics 8.3.204).
13
  - Weights exported as `.pt` checkpoints compatible with `ultralytics>=8.3`.
14
  - One model per label space; load the checkpoint that matches your target anatomy.
15
 
@@ -36,7 +39,7 @@ Multi-head release of three single-task segmentation models targeting NSFW anato
36
  ```python
37
  from ultralytics import YOLO
38
 
39
- model = YOLO("nsfw-seg-breast.pt") # swap for vagina or penis
40
  results = model.predict("path/to/image.jpg", imgsz=832, conf=0.1)
41
  ```
42
 
 
1
  # NSFW Segmentation
2
 
3
+ Multi-head release of single-task segmentation models targeting NSFW anatomy. Each checkpoint runs independently and produces binary masks for the specified classes.
4
 
5
+ | File | Backbone | Task | Classes | Mask mAP@0.5 | Mask mAP@0.5:0.95 |
6
+ | --- | --- | --- | --- | --- | --- |
7
+ | `nsfw-seg-breast-s.pt` | YOLO11s | Breast anatomy | breast, areola, nipple | 0.895 | 0.636 |
8
+ | `nsfw-seg-breast-x.pt` | YOLO11x | Breast anatomy | breast, areola, nipple | 0.929 | 0.702 |
9
+ | `nsfw-seg-vagina-s.pt` | YOLO11s | Vagina | vagina | 0.995 | 0.871 |
10
+ | `nsfw-seg-vagina-x.pt` | YOLO11x | Vagina | vagina | 0.995 | 0.918 |
11
+ | `nsfw-seg-penis-s.pt` | YOLO11s | Penis | penis | 0.995 | 0.975 |
12
+ | `nsfw-seg-penis-x.pt` | YOLO11x | Penis | penis | 0.995 | 0.987 |
13
 
14
  ## Description
15
+ - Backbones: YOLO11s and YOLO11x segmentation heads (Ultralytics 8.3.204).
16
  - Weights exported as `.pt` checkpoints compatible with `ultralytics>=8.3`.
17
  - One model per label space; load the checkpoint that matches your target anatomy.
18
 
 
39
  ```python
40
  from ultralytics import YOLO
41
 
42
+ model = YOLO("nsfw-seg-breast-s.pt") # swap for -x or other anatomy
43
  results = model.predict("path/to/image.jpg", imgsz=832, conf=0.1)
44
  ```
45