memoized_coduals
Shows that it is possible to implement reverse mode autodiff using a variation on the dual numbers called the codual numbers (by wlad-svennik)
MyGrad
Drop-in autodiff for NumPy. (by rsokl)
memoized_coduals | MyGrad | |
---|---|---|
2 | 1 | |
3 | 186 | |
- | - | |
2.6 | 3.0 | |
over 2 years ago | about 1 month ago | |
Python | Python | |
- | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
memoized_coduals
Posts with mentions or reviews of memoized_coduals.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Dual/Codual Numbers for Forward/Reverse Automatic Differentiation
I think this implementation and explanation is better: https://github.com/wlad-svennik/memoized_coduals
- Show HN: Efficient autodiff using codual numbers
MyGrad
Posts with mentions or reviews of MyGrad.
We have used some of these posts to build our list of alternatives
and similar projects.
What are some alternatives?
When comparing memoized_coduals and MyGrad you can also consider the following projects:
contextualise - Contextualise is an effective tool particularly suited for organising information-heavy projects and activities consisting of unstructured and widely diverse data and information resources
SmallPebble - Minimal deep learning library written from scratch in Python, using NumPy/CuPy.
pytorch_sparse - PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations