MobileNet-v3-Small: Image Classification

MobileNet-V3-Small is the lightweight version in the third generation of the MobileNet series, designed for resource-constrained devices like mobile and edge devices. Based on automated machine learning (AutoML) techniques, MobileNet-V3-Small incorporates depthwise separable convolutions, a hard-swish activation function, and a Squeeze-and-Excitation (SE) attention mechanism to boost performance and efficiency. Compared to MobileNet-V3-Large, MobileNet-V3-Small has a more compact architecture with fewer parameters, making it suitable for efficient image classification, object detection, and other tasks in low-power environments. Common applications on mobile include real-time face recognition, gesture control, and image classification, delivering high accuracy with fast processing capabilities.

Source model

  • Input shape: 224x224
  • Number of parameters: 2.42M
  • Model size: 9.71M
  • Output shape: 1x1000

Source model repository: MobileNet-v3-Small

Performance Reference

Please search model by model name in Model Farm

Inference & Model Conversion

Please search model by model name in Model Farm

License

Downloads last month
16
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support