MindSpore Lite Documentation

Filter Clear All Conditions

Environment

Windows Linux Mac Android iOS IoT

User

Beginner Intermediate Expert

Stage

Whole Process Environment Preparation Data Preparation Model Export Model Converting Model Loading Model Training Model Optimization Model Code Generation Model Obfuscator Inference Benchmark Testing Static Library Cropping Visualization

Application Specific Integrated Circuit

NPU NNIE TensorRT

Programming Language

C++ Java

---

Downloading MindSpore Lite

Welcome to MindSpore Lite. You can download the version package suitable for the local environment and use it directly.

Building MindSpore Lite

This chapter introduces how to quickly compile MindSpore Lite.

Experience C++ Simple Inference Demo

This tutorial provides a MindSpore Lite inference demo. It demonstrates the basic on-device inference process using C++ by inputting random data, executing inference, and printing the inference result.

Experience Java Simple Inference Demo

This tutorial provides an example program for MindSpore Lite to perform inference. It demonstrates the basic process of performing inference on the device side using MindSpore Lite Java API by random inputting data, executing inference, and printing the inference result.

Android Application Development Based on JNI Interface

It is recommended that you start from the image classification demo on the Android device to understand how to build the MindSpore Lite application project, configure dependencies, and use related APIs.

Android Application Development Based on Java Interface

This tutorial demonstrates the on-device deployment process based on the image segmentation demo on the Android device provided by the MindSpore team.

Implement Device Training Based On C++ Interface

This tutorial explains the code that trains a LeNet model using Training-on-Device infrastructure.

Implement Device Training Based On Java Interface

This tutorial demonstrates how to use the Java API on MindSpore Lite by building and deploying LeNet of the Java version.

Converting Models for Inference

MindSpore Lite provides a tool for offline model conversion. It supports conversion of multiple types of models. The converted models can be used for inference.

Optimizing the Model (Quantization After Training)

Converting a trained `float32` model into an `int8` model through quantization after training can reduce the model size and improve the inference performance. This tutorial introduces how to use the function.

Perform Inference on Mini and Small Systems

MindSpore Lite provides a code generator tool, namely codegen, which could have runtime compiling and computational graphs building done offline. Only necessary codes and information are kept in the generated program, thereby minimizing the size of the generated inference program.

Preprocessing Image Data

This tutorial introduces how to process the image data before inference to meet the data format requirements for model inference by creating a LiteMat object.

Using C++ Interface to Perform Inference

After model conversion using MindSpore Lite, the model inference process needs to be completed in Runtime. This tutorial introduces how to use C++ API to write inference code.

Using Java Interface to Perform Inference

After model conversion using MindSpore Lite, the model inference process needs to be completed in Runtime. This tutorial introduces how to use Java API to write inference code.

NPU Integration Information

This tutorial introduces the instructions for using the integrated NPU, including steps to use, supported chips, and supported operators.

Usage Description of the Integrated NNIE

This tutorial introduces instructions for using integrated NNIE.

TensorRT Integration Information

This tutorial introduces the instructions for using the integrated TensorRT.

Performing Benchmark Testing

After model conversion and before inference, you can use the Benchmark tool to perform benchmark testing on a MindSpore Lite model. It can not only perform quantitative analysis (performance) on the forward inference execution duration of a MindSpore Lite model, but also perform comparative error analysis (accuracy) based on the output of the specified model.

Static Library Cropper Tool

MindSpore Lite provides the libmindspore-lite.a static library cropping tool for runtime, which can filter out the operators in the ms model, crop the static library files, and effectively reduce the size of the library files.

Converting MindSpore ToD Models

This tutorial introduces that how to convert your MindSpore ToD(Train on Device) model.

Using C++ Interface to Perform Training

After model conversion using MindSpore Lite, the model training process needs to be completed in Runtime. This tutorial introduces how to use C++ API to write training code.

Performing Benchmark Testing of MindSpore ToD

You can use the net_train tool to perform benchmark testing on a MindSpore ToD (Train on Device) model. It can not only perform quantitative analysis (performance) on the execution duration the model, but also perform comparative error analysis (accuracy) based on the output of the specified model.

Visualization Tool

Netron is a neural network model visualization tool developed based on the Electron platform. Netron supports MindSpore Lite models, allowing you to easily view model information.

Model Obfuscation Tool

MindSpore Lite provides a lightweight offline model obfuscator to protect the confidentiality of model files deployed on the IoT devices.