MNASNet is a lightweight neural network architecture developed by Google, specifically designed for efficient image classification on mobile devices. MnasNet leverages automated machine learning (AutoML) with reinforcement learning to search for a network architecture that achieves an optimal balance between accuracy and latency. The MnasNet architecture builds on MobileNet’s depthwise separable convolutions, further optimizing computational efficiency. Compared to manually designed models, MnasNet offers excellent accuracy at lower computational costs, making it ideal for resource-constrained environments, such as mobile and embedded systems. This model is widely used in tasks like image classification and object detection, providing an efficient solution for mobile vision applications.

Source model

• Input shape: 224x224
• Number of parameters: 2.12M
• Model size: 8.45M
• Output shape: 1x1000

Source model repository: MNASNet

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the AIDLux AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md