torchsort
Fast, differentiable sorting and ranking in PyTorch (by teddykoker)
fast-soft-sort
Fast Differentiable Sorting and Ranking (by google-research)
torchsort | fast-soft-sort | |
---|---|---|
1 | 1 | |
742 | 546 | |
- | 0.9% | |
7.2 | 1.8 | |
5 months ago | 3 months ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
torchsort
Posts with mentions or reviews of torchsort.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-03-24.
fast-soft-sort
Posts with mentions or reviews of fast-soft-sort.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-03-24.
-
[P] Torchsort - Fast, differentiable sorting and ranking in PyTorch
The original implementation (https://github.com/google-research/fast-soft-sort) uses numba for the forward pass and pure python for the backwards pass, while Torchsort has both implemented in C++/CUDA with additional parallelization over the batch dimension. You can find some benchmarks in the Torchsort readme.
What are some alternatives?
When comparing torchsort and fast-soft-sort you can also consider the following projects:
google-research - Google Research
ranking - Learning to Rank in TensorFlow
thinc - 🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
recommenders - Best Practices on Recommendation Systems
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
CSrankings - A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
einops - Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
ivy - The Unified AI Framework