Skip to main content

Inference Engine Platform on Edge Device.

Project description

elangai

elangai is an inference engine platform designed for but not limited to the edge device. This SDK includes the main components of elangai.

Installation

Prerequisite

Before installing elangai, users have to install the following components:

  • TensorRT >= 7.0.0.11
  • TensorFlow >= 2.5.0
  • ONNXRuntime >= 1.5.2

Otherwise, elangai won't work as intended.

Install

elangai could be installed by following command.

pip3 install elangai

Quick Guide

Make Your Own AI App

Using the following command on terminal, you could easily generate the AI app.

elangai generate myapp

Dissect Your AI Model

Use the following command to examine the input and output tensor information of your AI model.

elangai model-dissector /path/to/your/model.onnx

Currently supports .onnx and .tflite file only.

Convert Your AI Model to .trt File

elangai only supports .tflite and .trt file inference. Use the following command to convert .onnx model to .trt file.

elangai model-converter --src /path/to/model.onnx  --dst /path/to/model.trt

Currently supports .onnx file conversion only.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

elangai-1.0.0.tar.gz (9.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

elangai-1.0.0-py3-none-any.whl (22.1 kB view details)

Uploaded Python 3

File details

Details for the file elangai-1.0.0.tar.gz.

File metadata

  • Download URL: elangai-1.0.0.tar.gz
  • Upload date:
  • Size: 9.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.10.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.6.9

File hashes

Hashes for elangai-1.0.0.tar.gz
Algorithm Hash digest
SHA256 418b9c76f59d6e20c8ce8034b5fc72541e8bd8ec704d613c0143d6f278c9ab94
MD5 4efc3cf4782aad1d67932e5d69e3f6a2
BLAKE2b-256 a6ca1987eb61dd18b52d5718fa7980b220c223c96ea260b8ce4d3a55dfd92380

See more details on using hashes here.

File details

Details for the file elangai-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: elangai-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 22.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.10.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.6.9

File hashes

Hashes for elangai-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 813356355b51bd6159b8169d5953488df0c196ad345a96babcb3cc5f47594315
MD5 aa6f349ec44c16f219bd12d4c0cd03fe
BLAKE2b-256 e84be44c3f3f2c47c56f61b53c8f0f0200738b218f9533de11a088ecc03baf31

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page