Hardware requirements#
Mobile installations#
Models provided in distribution package and supported devices.
| Neural network | ARM |
|---|---|
| FaceDet_v2_ |
yes |
| FaceDet_v2_ |
yes |
| FaceDet_v2_ |
yes |
| headpose_v3_ |
yes |
| ags_v3_ |
yes |
| eyes_estimation_flwr8_ |
yes |
| eye_status_estimation_ |
yes |
| mask_clf_v3_ |
yes |
| mouth_estimation_v4_ |
yes |
| face_occlusion_v1_ |
yes |
| model_subjective_quality_v1_ |
yes |
| model_subjective_quality_v2_ |
yes |
| glasses_estimation_flwr_v2_ |
yes |
| cnn54m_ |
yes |
| oneshot_rgb_liveness_v8_model_ |
yes |
| vlTracker_detection_ |
yes |
| vlTracker_template_ |
yes |
| vlTracker_update_ |
yes |
cnn54m_
.plan is provided in complete iOS FaceEngine SDK edition only.
CPU requirements#
arm64 is provided within iOS frameworks.
Bitcode-enabled libraries are available for iOS.
Memory requirements#
RAM requirements are given for common for mobile platform verification pipeline.
Storage is amount of space specific version of installation takes on device. For iOS app thinning before deployment is assumed. As the result *.frameworks files in your final app archive will occupy (up to 30-60%, depending on platform) less storage space compared to ones found in the distribution.
"Memory requirements"
| Requirements for | iOS |
|---|---|
| RAM | 400 MB |
| Storage Full | 200 MB |
| Storage Frontend | 170 MB |
Number of threads on mobile devices#
The description of according settings you can find in "Configuration Guide - Runtime settings". The setting <param name="numThreads" type="Value::Int1" x="-1" /> means that will be taken the maximum number of available threads. This number of threads is equal to according number of available processor cores. We strongly recommend you to follow this recommendation; otherwise, performance can be significantly reduced.