Explore projects
-
Aidge's reference CPU backend, written in C++, not optimized for performances
Updated -
Updated
-
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
Updated -
Updated
-
Aidge's OpenCV backend, written in C++, for image data loading and some CV operators implementation
Updated -
Updated
-
Aidge's core module, written in C++, always required
Updated -
Updated
-
Updated
-
Updated
-
Aidge's reference C++ export module, required for generating standalone C++ static compute graph
Updated -
Aidge's TensorRT export module. It act as a thin wrapper around NVidia's tools with easy custom operator insertion
Updated -
Aidge's learning module, written in C++, required for models training directly in Aidge
Updated -
Module template for creating a new Aidge module
Updated -
Aidge's quantization module, for both PTQ and QAT, written in C++
Updated