Neural Network Models¶
Here you can see a summary for neural network models created by our Lab and used in FindFace Security:
Important
The default face biometrics model upon a clean install is ifruit_320.
| Model | Type |
|---|---|
| face/ifruit_160 | Face biometrics |
| face/ifruit_320 | |
| faceattr/age.v1 | Age recognition |
| faceattr/beard.v0 | Beard recognition |
| faceattr/emotions.v1 | Emotions recognition |
| faceattr/gender.v2 | Gender recognition |
| faceattr/glasses3.v0 | Glasses recognition |
| faceattr/medmask3.v2 | Face mask detection |
| faceattr/liveness.alleyn | Liveness standalone service |
| faceattr/quality.v1 | Face quality estimation |
Note
The CPU and GPU benchmark setup is the following:
- CPU - Intel® Core™ i7-6700 CPU @ 3.4GHz 4 cores
- GPU - GeForce GTX 1080 Ti
Benchmark results for CPU-accelerated models:
Note
Features in the benchmark result below: faceattr/age.v1.cpu, faceattr/beard.v0.cpu, faceattr/emotions.v1.cpu, faceattr/gender.v2.cpu, faceattr/glasses3.v0.cpu.
| Model | # instances | RAM, Mb | # instances | RAM, Mb | # instances | RAM, Mb | # instances | RAM, Mb | # instances | RAM, Mb |
|---|---|---|---|---|---|---|---|---|---|---|
| face/ifruit_320.cpu | 1 | 4300 | 2 | 5020 | 3 | 5698 | 4 | 7606 | 5 | 8279 |
| face/ifruit_160.cpu | 2732 | 3973 | 4754 | 5415 | 6105 | |||||
| face/ifruit_320.cpu + features | 6254 | 7019 | 7725 | 8597 | 9220 | |||||
|
4645 | 5673 | 6329 | 7023 | 7649 | |||||
| face/ifruit_320.cpu + features + edie_rc2.cpu.fnk | 6513 | 7454 | 9165 | 9685 | 10777 | |||||
| face/ifruit_160.cpu + features + edie_rc2.cpu.fnk | 5197 | 6355 | 7113 | 8052 | 8881 | |||||
| features | 3034 | 3799 | 4460 | 5091 | 5774 | |||||
| features + medmask3.v2.cpu | 3191 | 3942 | 4699 | 5313 | 6003 | |||||
| face/ifruit_320.cpu + medmask3.v2.cpu | 4447 | 5108 | 5809 | 7642 | 8262 | |||||
| face/ifruit_160.cpu + medmask3.v2.cpu | 2913 | 4291 | 4947 | 5571 | 6093 | |||||
| face/ifruit_320.cpu + edie_rc2.cpu.fnk | 4583 | 5557 | 7746 | 8721 | 9592 |
Benchmark results for GPU-accelerated models:
Note
Features in the benchmark result below: faceattr/age.v1.gpu.fnk, faceattr/beard.v0.gpu.fnk, faceattr/emotions.v1.gpu.fnk, faceattr/gender.v2.gpu.fnk, faceattr/glasses3.v0.gpu.fnk.
| Model | GPU RAM, Mb |
|---|---|
| face/ifruit_160.gpu.fnk | 2913 |
| face/ifruit_160.gpu.fnk + edie_rc2.gpu.fnk | 4115 |
| face/ifruit_160.gpu.fnk + features | 3771 |
| face/ifruit_160.gpu.fnk + features + edie_rc2.gpu.fnk | 4974 |
| face/ifruit_160.gpu.fnk + faceattr/medmask3.v2.gpu.fnk | 3185 |
| face/ifruit_320.gpu.fnk | 3169 |
| face/ifruit_320.gpu.fnk + edie_rc2.gpu.fnk | 4243 |
| face/ifruit_320.gpu.fnk + features | 3901 |
| face/ifruit_320.gpu.fnk + features + edie_rc2.gpu.fnk | 5102 |
| face/ifruit_320.gpu.fnk + faceattr/medmask3.v2.gpu.fnk | 3313 |
| features | 2345 |
| features + faceattr/medmask3.v2gpu.fnk | 2617 |