Path to this page:
NOTICE: This package has been removed from pkgsrc./
wip/py-autograd,
Efficiently computes derivatives of numpy code
Branch: CURRENT,
Version: 1.3,
Package name: py310-autograd-1.3,
Maintainer: jihbed.researchAutograd can automatically differentiate native Python
and Numpy code. It can handle a large subset of Python
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
Master sites:
RMD160: 4566e05e7ca36c37b3b804d60b7610cc8b3c04ef
Filesize: 37.36 KB
Version history: (Expand)
- (2023-05-16) Package deleted from pkgsrc
- (2023-02-13) Package has been reborn
- (2023-02-13) Updated to version: py310-autograd-1.3
- (2021-10-08) Updated to version: py39-autograd-1.3
- (2020-10-26) Package added to pkgsrc.se, version py37-autograd-1.3 (created)