long-range-arena
scenic
Our great sponsors
long-range-arena | scenic | |
---|---|---|
6 | 5 | |
682 | 2,995 | |
2.9% | 5.8% | |
0.0 | 8.6 | |
4 months ago | 2 days ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
long-range-arena
-
The Secret Sauce behind 100K context window in LLMs: all tricks in one place
https://github.com/google-research/long-range-arena
-
[R] The Annotated S4: Efficiently Modeling Long Sequences with Structured State Spaces
The Structured State Space for Sequence Modeling (S4) architecture is a new approach to very long-range sequence modeling tasks for vision, language, and audio, showing a capacity to capture dependencies over tens of thousands of steps. Especially impressive are the model’s results on the challenging Long Range Arena benchmark, showing an ability to reason over sequences of up to 16,000+ elements with high accuracy.
-
[D] Is there a repo on which many light-weight self-attention mechanism are introduced?
1.1 Long Range Arena: A Benchmark for Efficient Transformers. From authors of above, they proposed a benchmark for modeling long range interactions. It also inlcudes a repository
- [R] Google’s H-Transformer-1D: Fast One-Dimensional Hierarchical Attention With Linear Complexity for Long Sequence Processing
- [2107.11906] H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences
-
[R][D] Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Zhou et al. AAAI21 Best Paper. ProbSparse self-attention reduces complexity to O(nlogn), generative style decoder to obtainsequence output in one step, and self-attention distilling for further reducing memory
I think the paper is written in a clear style and I like that the authors included many experiments, including hyperparameter effects, ablations and extensive baseline comparisons. One thing I would have liked is them comparing their Informer to more efficient transformers (they compared only against logtrans and reformer) using the LRA (https://github.com/google-research/long-range-arena) benchmark.
scenic
-
Vid2Seq: A pretrained visual language model for describing multi-event videos
Anyone figured out how to run this against a video?
https://github.com/google-research/scenic/tree/main/scenic/p... has an example showing how to "train Vid2Seq on YouCook2" using "python -m scenic.projects.vid2seq.main", but I couldn't see the recipe for using it against a video to return a description.
-
[D] SE for machine learning reaserch
There are a few libraries/frameworks that one can use and allow to reuse the same code for datasets, logging, training loop etc.... . E.g. Lightning or Scenic. Maybe you can use one of these or at least get some inspiration for your own code.
-
Google Research Proposes an Artificial Intelligence (AI) Model to Utilize Vision Transformers on Videos
Quick Read: https://www.marktechpost.com/2022/11/25/google-research-proposes-an-artificial-intelligence-ai-model-to-utilize-vision-transformers-on-videos/ Paper: https://openaccess.thecvf.com/content/ICCV2021/papers/Arnab\_ViViT\_A\_Video\_Vision\_Transformer\_ICCV\_2021\_paper.pdf Github link: https://github.com/google-research/scenic/tree/main/scenic/projects/vivit
-
Google Research Introduces ‘SCENIC’: An Open-Source JAX Library For Computer Vision Research
GitHub: https://github.com/google-research/scenic
-
[R] Google Open-Sources SCENIC: A JAX Library for Rapid Computer Vision Model Prototyping and Cutting-Edge Research
The SCENIC code, etc., has been open-sourced on the project’s GitHub. The paper SCENIC: A JAX Library for Computer Vision Research and Beyond is on arXiv.
What are some alternatives?
performer-pytorch - An implementation of Performer, a linear attention-based transformer, in Pytorch
attention-is-all-you-need-pytorch - A PyTorch implementation of the Transformer model in "Attention is All You Need".
jax-resnet - Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).
HJxB - Continuous-Time/State/Action Fitted Value Iteration via Hamilton-Jacobi-Bellman (HJB)
manga-ocr - Optical character recognition for Japanese text, with the main focus being Japanese manga
EasyCV - An all-in-one toolkit for computer vision
tldr-transformers - The "tl;dr" on a few notable transformer papers (pre-2022).
elegy - A High Level API for Deep Learning in JAX
asreview - Active learning for systematic reviews