initial readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model Card
|
| 2 |
+
|
| 3 |
+
SynthPar2 is a conditional StyleGAN2 model capable of creating synthetic face images with specified attributes like skin color and sex.
|
| 4 |
+
It is built upon the StyleGAN2 architecture and trained on the VGGFace2 dataset.
|
| 5 |
+
|
| 6 |
+
# Intended Use
|
| 7 |
+
|
| 8 |
+
The primary intended use of this model is to generate synthetic face images with a good representation across various skin colors.
|
| 9 |
+
|
| 10 |
+
These generated images can be utilized for various purposes, such as:
|
| 11 |
+
|
| 12 |
+
- Developing and evaluating face recognition models with the goal of reducing performance disparities across different demographic groups.
|
| 13 |
+
|
| 14 |
+
- Augmenting existing face datasets to improve their representation of diverse skin colors.
|
| 15 |
+
|
| 16 |
+
- Conducting research on fairness and bias in facial recognition systems.
|
| 17 |
+
|
| 18 |
+
# How to Use
|
| 19 |
+
|
| 20 |
+
Please refer to the github [repo](https://github.com/pravsels/SynthPar2) for further guidance.
|
| 21 |
+
|
| 22 |
+
# License
|
| 23 |
+
|
| 24 |
+
The SynthPar2 model is released under the MIT license.
|