tensortrax
Math on (Hyper-Dual) Tensors with Trailing Axes (by adtzlr)
neograd
A deep learning framework created from scratch with Python and NumPy (by pranftw)
tensortrax | neograd | |
---|---|---|
1 | 2 | |
7 | 230 | |
- | - | |
6.8 | 0.0 | |
11 days ago | over 1 year ago | |
Python | Python | |
GNU General Public License v3.0 only | GNU General Public License v3.0 only |
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.
tensortrax
Posts with mentions or reviews of tensortrax.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Tensortrax: A python package for gradient and hessian evaluations (by forward-mode AD / hyper-dual numbers) of functions.
Motivation and personal usage: For the gradient as well as the hessian of the strain energy function used for the (mechanical) stress evaluation of hyperelastic solids I needed a fast automatic differentiation package for simulations I'll have to perform for my PhD thesis. During finite element simulations, such a function must be evaluated for thousands or even millions of 3x3 tensors. Therefore, tensortrax supports input arrays with (but of course, optional) trailing axes.
neograd
Posts with mentions or reviews of neograd.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-10-21.
-
This Week in Python
neograd – A deep learning framework created from scratch with Python and NumPy
-
neograd - A deep learning framework created from scratch using Python and NumPy
Checkout the GitHub repo - https://github.com/pranftw/neograd
What are some alternatives?
When comparing tensortrax and neograd you can also consider the following projects:
pihole-regex - Custom RegEx, Exact, and Adlist filters for Pi-hole's FTLDNS
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
codex_english2python - Converts plain english to python code snippets by using OpenAI CODEX.
section-properties - Analysis of an arbitrary cross-section in python using the finite element method.
ivy - The Unified Machine Learning Framework [Moved to: https://github.com/unifyai/ivy]
ldapcherry - Web UI for managing users and groups in multiple directory services.