This is a convert tool to create AIfES models for direct use in the Arduino IDE or other IDEs
Project description
AIfES-Converter
This is a convert tool to create AIfES models for direct use in the Arduino IDE or other IDEs. It can read Feed Forward Neural Networks (FFNN) models from Keras and PyTorch and converts them to AIfES models, which are exported in header files. Those header files can than be added to your Project in any IDE and can be used there.
Quick Start
Install the converter:
pip install AIfES-Converter
IMPORTANT: For a detailed description of the installation see the documentation
Convert a Keras model, e.g.:
from aifes import keras2aifes
keras2aifes.convert_to_fnn_f32_express(model, 'path/to/location')
Convert a PyTorch model, e.g.:
from aifes import pytorch2aifes
pytorch2aifes.convert_to_fnn_f32_express(model, 'path/to/location')
Documentation
For a detailed documentation see here.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file AIfES-Converter-1.0.0.tar.gz
.
File metadata
- Download URL: AIfES-Converter-1.0.0.tar.gz
- Upload date:
- Size: 34.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.8.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 458744bde207304aed6e3be6a84d68c51b0aa8c2774faf6ed1a778a17543d4a0 |
|
MD5 | 87c33e356afd39bd5b177cc8a518c49f |
|
BLAKE2b-256 | 677bc727b93fe9ece22f422d85c0ba34b0fb4cea740ec1ff38aa110b5a9700e2 |
File details
Details for the file AIfES_Converter-1.0.0-py3-none-any.whl
.
File metadata
- Download URL: AIfES_Converter-1.0.0-py3-none-any.whl
- Upload date:
- Size: 53.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.8.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b2133aa9512017c4f8fbda7fe24658c0f399bd4177c1236ae2d77e418eb57382 |
|
MD5 | d1164794f877494d5e5cff90b325c1f5 |
|
BLAKE2b-256 | 71ba682171b2d66de14b23ea61fe471e064528de6a421d7b7c942930abc3cefe |