Explore projects

The Trustable Software Framework (TSF) provides an extensible model for collecting, organising and evaluating evidence for releases of a software project or product, to allow a consumer to consider to what extent they should trust the software. Documentation: https://codethinklabs.gitlab.io/trustable/trustable/

Aidge bundle repository, which includes the main modules of the Aidge framework, plus the documentation and tutorials.

Aidge's core module, written in C++, always required

Aidge's reference C++ export module, required for generating standalone C++ static compute graph

Aidge's quantization module, for both PTQ and QAT, written in C++

Aidge's ONNX import/export module, written in Python, required for ONNX interoperability

Graph viewer for Aidge based on Model Explorer

Aidge's learning module, written in C++, required for models training directly in Aidge

Aidge's TensorRT export module. It act as a thin wrapper around NVidia's tools with easy custom operator insertion

Aidge's C++ export module optimized for ARM Cortex-M

Aidge's CUDA backend, written in C++/CUDA and using NVidia's CuDNN and CuBLAS libraries. Required for training and inference on NVidia's GPUs

Aidge's reference CPU backend, written in C++, not optimized for performances

Aidge's core module, written in C++, always required

Aidge's OpenCV backend, written in C++, for image data loading and some CV operators implementation

Aidge's pruning module, written in C++

Aidge's ONNX import/export module, written in Python, required for ONNX interoperability

Aidge's ONNX import/export module, written in Python, required for ONNX interoperability