autograd
Efficiently computes derivatives of numpy code.
Autograd can automatically differentiate native Python and Numpy code. It can handle a large subset of Python's features, including loops, ifs, recursion and closures, and it can even take derivatives of derivatives of derivatives. It supports reverse-mode differentiation (a.k.a. backpropagation), which means it can efficiently take gradients of scalar-valued functions with respect to array-valued arguments, as well as forward-mode differentiation, and the two can be composed arbitrarily. The main intended application of Autograd is gradient-based optimization.
homepage ↗ pypi: autograd github: HIPS/autograd
Available in
| Overlay | Newest | Ebuilds | Last activity | |
|---|---|---|---|---|
| science gitweb ↗ | 1.8.0 | 2 | 4 d | details › |
Versions & arches
Use flags of 1.8.0
- test Enable dependencies and/or preparations necessary to run tests (usually controlled by FEATURES=test but can be toggled independently)
2 expansion flags (python targets, ABIs, cpu flags…)
- python_targets_python3_12
- python_targets_python3_13
Runtime dependencies of 1.8.0
show 8 lines
python_targets_python3_12?
(
)
python_targets_python3_13?
(
)