| Custom-build | Base library | CPU | GPU | Face detection model / accuracy on WIDER Face (Hard) | Face recognition model / accuracy on LFW | Age and gender detection | Face mask detection | Comment |
|---|---|---|---|---|---|---|---|---|
| FaceNet (default) | FaceNet | x86 (AVX instructions) | not supported | MTCNN / 80.9% | FaceNet (20180402-114759) / 99.63% | Custom, the model is taken here | Custom model | For general purposes. Support CPU without AVX2 |
| FaceNet Masked (Experimental) | FaceNet | x86 (AVX instructions) | not supported | MTCNN / 80.9% | inception_v3_on_mafa_kaggle123 / 98.73% | Custom, the model is taken here | Custom model | For general purposes. Support CPU without AVX2 |
| Mobilenet | InsightFace | x86 (AVX2 instructions) | not supported | RetinaFace-MobileNet0.25 / 82.5% | MobileFaceNet,ArcFace / 99.50% | InsightFace | Custom model | The fastest model among CPU only models |
| Mobilenet-gpu | InsightFace | x86 (AVX2 instructions) | GPU (CUDA required) | RetinaFace-MobileNet0.25 / 82.5% | MobileFaceNet,ArcFace / 99.50% | InsightFace | Custom model | The fastest model |
| SubCenter-ArcFace-r100 | InsightFace | x86 (AVX2 instructions) | not supported | retinaface_r50_v1 / 91.4% | arcface-r100-msfdrop75 / 99.80% | InsightFace | Custom model | The most accurate model, but the most slow |
| SubCenter-ArcFace-r100-gpu | InsightFace | x86 (AVX2 instructions) | GPU (CUDA required) | retinaface_r50_v1 / 91.4% | arcface-r100-msfdrop75 / 99.80% | InsightFace | Custom model | The most accurate model |
custom-builds
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|
parent directory.. | ||||