Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,50 @@ model-index:
|
|
| 22 |
- name: top1_acc
|
| 23 |
type: top1_acc
|
| 24 |
value: 0.717
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
---
|
| 26 |
# Race Classification YOLOv8/11
|
| 27 |
This model is based on [FairFace](https://github.com/joojs/fairface) 0.25 padding variant dataset composed by Microsoft researchers, aiming to reduce bias by better balancing classes in dataset.
|
|
|
|
| 22 |
- name: top1_acc
|
| 23 |
type: top1_acc
|
| 24 |
value: 0.717
|
| 25 |
+
- name: v8s
|
| 26 |
+
results:
|
| 27 |
+
- task:
|
| 28 |
+
type: Image Classification
|
| 29 |
+
dataset:
|
| 30 |
+
name: FairFace
|
| 31 |
+
type: FairFace
|
| 32 |
+
metrics:
|
| 33 |
+
- name: top1_acc
|
| 34 |
+
type: top1_acc
|
| 35 |
+
value: 0.721
|
| 36 |
+
- name: v8m
|
| 37 |
+
results:
|
| 38 |
+
- task:
|
| 39 |
+
type: Image Classification
|
| 40 |
+
dataset:
|
| 41 |
+
name: FairFace
|
| 42 |
+
type: FairFace
|
| 43 |
+
metrics:
|
| 44 |
+
- name: top1_acc
|
| 45 |
+
type: top1_acc
|
| 46 |
+
value: 0.725
|
| 47 |
+
- name: 11l
|
| 48 |
+
results:
|
| 49 |
+
- task:
|
| 50 |
+
type: Image Classification
|
| 51 |
+
dataset:
|
| 52 |
+
name: FairFace
|
| 53 |
+
type: FairFace
|
| 54 |
+
metrics:
|
| 55 |
+
- name: top1_acc
|
| 56 |
+
type: top1_acc
|
| 57 |
+
value: 0.733
|
| 58 |
+
- name: 11x
|
| 59 |
+
results:
|
| 60 |
+
- task:
|
| 61 |
+
type: Image Classification
|
| 62 |
+
dataset:
|
| 63 |
+
name: FairFace
|
| 64 |
+
type: FairFace
|
| 65 |
+
metrics:
|
| 66 |
+
- name: top1_acc
|
| 67 |
+
type: top1_acc
|
| 68 |
+
value: 0.735
|
| 69 |
---
|
| 70 |
# Race Classification YOLOv8/11
|
| 71 |
This model is based on [FairFace](https://github.com/joojs/fairface) 0.25 padding variant dataset composed by Microsoft researchers, aiming to reduce bias by better balancing classes in dataset.
|