Skip to content
Snippets Groups Projects
Olivier BICHLER's avatar
Olivier BICHLER authored
Fix loss derivative

See merge request !43
d2e420ea
History

aidge_learning

In this module, you can find functions and classes to train your models:

  • Optimizer (SGD)
  • LRScheduler (ConstantLR, StepLR)
  • loss functions (MSE)

Dependencies

  • GCC
  • Make/Ninja
  • CMake
  • Python (optional, if you have no intend to use this library in python with pybind)

Aidge dependencies

  • aidge_core
  • aidge_backend_cpu

Pip installation

pip install . -v

TIPS : Use environment variables to change compilation options :

  • AIDGE_INSTALL : to set the installation folder. Defaults to /usr/local/lib. ⚠️ This path must be identical to aidge_core install path.
  • AIDGE_PYTHON_BUILD_TYPE : to set the compilation mode to Debug or Release
  • AIDGE_BUILD_GEN : to set the build backend with

C++ installation

./setup.sh -m core -m backend_cpu -m learning --release