MobileFaceNet
Lightweight real‑time face verification on‑device.
MobileFaceNet is an efficient CNN that maps a 112x112 face image to a compact 128‑dimensional embedding. Two embeddings are compared via cosine similarity to determine whether they belong to the same person, achieving 99.48% accuracy on the LFW benchmark. The model uses depthwise‑separable convolutions and inverted residual blocks (MobileNetV2‑style) to stay under 1M parameters, making it well‑suited for real‑time face verification on mobile and edge devices. Trained with ArcFace loss on MS‑Celeb‑1M.
Not supported
This model is currently not supported on any IoT chipset.
To see performance metrics for this model on other chipsets, click the button below.
View for other chipsetsTechnical Details
Embedding dimension:128
Input resolution:112x112
Model checkpoint:mobilefacenet.pt
Model size (float):4MB
Number of parameters:1M
Applicable Scenarios
- Incabinet driver monitoring
- phone unlocking
- building access control.
License
Model:APACHE-2.0
Tags
- real-time
Supported IoT Devices
- Arduino VENTUNO Q
- Dragonwing IQ-8275 EVK
- Dragonwing IQ-9075 EVK
- Dragonwing IQ-X5121
- Dragonwing IQ-X7181
- Dragonwing Q-6690 MTP
- Dragonwing Q-7790
- Dragonwing Q-8750
- Dragonwing RB3 Gen 2 Vision Kit
- QCS8550 (Proxy)
Supported IoT Chipsets
- Qualcomm® Dragonwing™ Q-6690
- Qualcomm® QCS5121
- Qualcomm® Dragonwing™ QCS6490
- Qualcomm® Dragonwing™ IQ-X7181
- Qualcomm® Dragonwing™ Q-7790
- Qualcomm® Dragonwing™ IQ-8275
- Qualcomm® Dragonwing™ QCS8550 (Proxy)
- Qualcomm® Dragonwing™ Q-8750
- Qualcomm® Dragonwing™ IQ-9075
Related Models
See all models
Looking for more? See models created by industry leaders.
Discover Model Makers