MobileNet V2 224x224 Quantized
Model Overview
A quantized MobileNet V2 model with a 1.0 width multiplier optimized for image classification on ImageNet at 224x224 resolution.
The MobileNet V2 1.0 224 Quant model is developed and optimized for the Synaptics Astra™ SL2610-Series processors with Torq NPU.
Model Features
- Model Type: Image Classification
- Input Size: 224x224
- Output Size: 1x1000
Deployment
The compiled model file is available for download on Huggingface at Synaptics/MobileNetV2.
Usage tutorial available at Synaptics AI Developer Zone / SL2600 / Image Classification.
Performance on NPU
| Processors | Inference Time (ms) |
|---|---|
| SL2619 | 7.035 |
License
The source model is licensed under Apache License 2.0.
The compiled model for on-device deployment is covered under the Synaptics Astra EULA.
Learn More
- Synaptics AI Developer Zone: Get started with documentation, tutorials and resources for your Edge AI journey.
- Astra Support Portal: Connect with our engineering team and community.
Related models
MobileNet V2 1.0 224 Quant
A quantized MobileNet V2 model with a 1.0 width multiplier optimized for image classification on ImageNet at 224x224 resolution.
MobileNet V2 1.0 224 Float
A MobileNet V2 model with a 1.0 width multiplier optimized for image classification on ImageNet at 224x224 resolution.
MobileNet V1 0.25 224 Quant
A quantized MobileNet V1 model with a 0.25 width multiplier optimized for image classification on ImageNet at 224x224 resolution.
MobileNet V1 0.25 224 Float
A MobileNet V1 model with a 0.25 width multiplier optimized for image classification on ImageNet at 224x224 resolution.
Inception V4 299 Quant
A quantized Inception V4 model optimized for image classification on ImageNet at 299x299 resolution.