No project description provided
Project description
A brief guide to Acuitylite
Acuitylite is an end-to-end neural-network deployment tool for embedded systems.
Acuitylite support converting caffe/tflite model to TIM-VX case.
In addition, Acuitylite support asysmetric uint8 qutization.
System Requirement
Processor: Intel Core i5-6500 CPU @ 3.20GHz x 4 (need to support the avx instruction set) Memory: 4GB RAM (at least) OS: Ubuntu Linux 20.04 LTS 64-bit (recommend)
Install
pip install acuitylite
Document
Reference: https://github.com/VeriSilicon/acuitylite/doc/index.html
Framework Support
How to run TIM-VX case
The exported TIM-VX case supports both make and cmake.
Please set environment for build and run case:
- TIM_VX_DIR=/path/to/tim-vx/build
- VIVANTE_SDK_DIR=/path/to/tim-vx/prebuilt-sdk/x86_64_linux
- LD_LIBRARY_PATH=$TIM_VX_DIR/lib:$VIVANTE_SDK_DIR/lib
Attention: The TIM_VX_DIR path should include lib and header files of TIM-VX. You can refer TIM-VX to build TIM-VX.
Support
Create issue on github or email to ML_Support@verisilicon.com
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Hashes for acuitylite-6.0.0-cp38-cp38-manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 716ce6fe1336748a5cb8945e50395a5a30633decf4b99b068dce1973e78e3ee9 |
|
MD5 | ab61a4e08576f41f9eeb7da00e1852a1 |
|
BLAKE2b-256 | e8b16fb26bfe822c6000c0a78b06fe50659fac5f43702ba106cec98b0a0e26eb |