Minimal automatic differentiation implementation in Python, NumPy.
Project description
SmallPebble
Minimal automatic differentiation implementation in Python, NumPy.
For an introduction to autodiff and the basic concepts of this framework, see: https://sidsite.com/posts/autodiff/
Consider this a resource on autodiff, rather than a library you should use. (Popular libraries are: JAX, PyTorch, TensorFlow...)
Features:
- Various operations, such as matmul, conv2d, maxpool2d.
- Supports broadcasting.
- Nth derivatives.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
smallpebble-0.1.1.tar.gz
(13.5 kB
view hashes)
Built Distribution
Close
Hashes for smallpebble-0.1.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 5df2b7a0072d222135939ed1eb33387f3a8d07d215c6dd666c8c1d717593cffe |
|
| MD5 | 1d52586eac39fc80d1c206768a2f4989 |
|
| BLAKE2b-256 | d9d2292f2951c9f1552d473bebcefa6a8be1c8b0d94faaf1ac008856e128d90d |
