github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-07 03:55:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

accuracy scores of models updated

Browse Source
This commit is contained in:
Sefik Ilkin Serengil 2024-03-17 11:53:11 +00:00
parent ee63d8b902
commit 5e3d415105
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@ -140,16 +140,16 @@ FaceNet, VGG-Face, ArcFace and Dlib are [overperforming](https://youtu.be/i_MOwv
| Model | Declared LFW Score | | Model | Declared LFW Score |
| --- | --- | | --- | --- |
| VGG-Face | 98.78% | | VGG-Face | 98.9% |
| Facenet | 99.20% | | Facenet | 99.2% |
| Facenet512 | 99.65% | | Facenet512 | 99.6% |
| OpenFace | 93.80% | | OpenFace | 92.9% |
| DeepID | - | | DeepID | - |
| Dlib | 99.38 % | | Dlib | 97.4 % |
| SFace | 99.60% | | SFace | 99.5% |
| ArcFace | 99.41% | | ArcFace | 99.5% |
| GhostFaceNet | 99.76 | | GhostFaceNet | 99.7% |
| *Human-beings* | *97.53%* | | *Human-beings* | *97.5%* |
Conducting experiments with those models within DeepFace may reveal disparities compared to the original studies, owing to the adoption of distinct detection or normalization techniques. Furthermore, some models have been released solely with their backbones, lacking pre-trained weights. Thus, we are utilizing their re-implementations instead of the original pre-trained weights. Conducting experiments with those models within DeepFace may reveal disparities compared to the original studies, owing to the adoption of distinct detection or normalization techniques. Furthermore, some models have been released solely with their backbones, lacking pre-trained weights. Thus, we are utilizing their re-implementations instead of the original pre-trained weights.