PkgFoundry
Catalog PyPI
Back to packageRELEASE DETAILS

6.18.0

PyPI

acuitypro

# A brief guide to Acuitylite Acuitylite is an end-to-end neural-network deployment tool for embedded systems.<br/> Acuitylite support converting caffe/darknet/onnx/tensorflow/tflite models to TIM-VX/TFLite cases. In addition, Acuitylite support asymmetric uint8 and symmetric int8 quantization. ### System Requirement - OS: Ubuntu Linux 20.04 LTS 64-bit (recommend) - Python Version: python3.8 (needed) ### Install pip install acuitylite ### Document Reference: https://verisilicon.github.io/acuitylite ### Framework Support - Importer: [Caffe](https://github.com/BVLC/caffe), [Darknet](https://github.com/pjreddie/darknet), [Onnx](https://github.com/onnx/onnx), [Tensorflow](https://github.com/tens

Published4 Apr 2023
Direct dependencies7
Transitive dependenciesNot calculated

README

Version 6.18.0 documentation

A brief guide to Acuitylite

Acuitylite is an end-to-end neural-network deployment tool for embedded systems.
Acuitylite support converting caffe/darknet/onnx/tensorflow/tflite models to TIM-VX/TFLite cases. In addition, Acuitylite support asymmetric uint8 and symmetric int8 quantization.

System Requirement

  • OS: Ubuntu Linux 20.04 LTS 64-bit (recommend)
  • Python Version: python3.8 (needed)

Install

pip install acuitylite

Document

Reference: https://verisilicon.github.io/acuitylite

Framework Support

Tips: You can export a TFLite app and using tflite-vx-delegate to run on TIM-VX if the exported TIM-VX app does not meet your requirements.

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/install
  • 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

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Declared dependencies 7

Native requirements
7 direct targetsNot calculated transitive count
Package / targetRequirementRelationship
dill
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
dill (==0.2.8.2)runtime
lmdb
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
lmdb (==0.93)runtime
networkx
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
networkx (>=1.11)runtime
onnx
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
onnx (<=1.11.0,>=1.8.0)runtime
ply
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
ply (==3.11)runtime
ruamel.yaml
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
ruamel.yaml (==0.15.81)runtime
tensorflow
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
tensorflow (<=2.8.0,>=2.3.0)runtime

Distribution files

1 collected
acuitypro-6.18.0-py3-none-manylinux2010_x86_64.whl

bdist_wheel · 1.87 KB · Python py3

Source file

Metadata history

Meaningful changes
Current collected state Current

Observed since 20 Oct, 18:43 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package_version:a39d3de252b1bde08db0ff2c601cb03c96e248419b9ff929d2cfed7fec06fa75

Other collected versions

View all collected versions →