Perceiver
gato
| Perceiver | gato | |
|---|---|---|
| 7 | 3 | |
| 85 | 446 | |
| - | 3.6% | |
| 2.6 | 7.7 | |
| about 3 years ago | 10 days ago | |
| Python | Python | |
| MIT License | 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.
Perceiver
- I implemented Deepmind's new Perceiver Model
- I Implemented Deepmind's Perceiver Model
-
[P] I implemented DeepMind's "Perceiver" in PyTorch
Great one, I implemented the Perceiver model too in TensorFlow: https://github.com/Rishit-dagli/Perceiver
- Deepmind's New Perceiver Model
-
[P] Implementing Perceiver: General perception with Iterative Attention in TensorFlow
The project: https://github.com/Rishit-dagli/Perceiver
- Perceiver, General Perception with Iterative Attention
gato
-
We Executed a Critical Supply Chain Attack on PyTorch
Yup! This is what makes this kind of attack scary and very unique to GitHub Actions. The baseline GITHUB_TOKEN just blows the door open on lateral movement via workflow_dispatch and and repository_dispatch events.
In several of our other operations, not just PyTorch, we leveraged workflow_dispatch to steal a PAT from another workflows. Developers tend to over-provision PATs so often. More often than not we'd end up with a PAT that has all scopes checked and org admin permissions. With that one could clean out all of the secrets from an organization in minutes using automated tools such as https://github.com/praetorian-inc/gato.
- gato: GitHub Self-Hosted Runner Enumeration and Attack Tool - an enumeration and attack tool that allows both blue teamers and offensive security practitioners to evaluate the blast radius of a compromised personal access token within a GitHub organization.
- Gato (Github Attack TOolkit), a tool to enumerate, attack, and defend GitHub Actions self-hosted runners
What are some alternatives?
Swin-Transformer-Object-Detection - This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.
bertviz - BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
performer-pytorch - An implementation of Performer, a linear attention-based transformer, in Pytorch
athena - an open-source implementation of sequence-to-sequence based speech processing engine
Fast-Transformer - An implementation of Fastformer: Additive Attention Can Be All You Need, a Transformer Variant in TensorFlow
TimeSformer-pytorch - Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
gato - Unofficial Gato: A Generalist Agent
deepmind-perceiver - My implementation of DeepMind's Perceiver
conformer - Implementation of the convolutional module from the Conformer paper, for use in Transformers
EQTransformer - EQTransformer, a python package for earthquake signal detection and phase picking using AI.
HTM-pytorch - Implementation of Hierarchical Transformer Memory (HTM) for Pytorch
DECIMER-Image_Transformer - DECIMER: Deep Learning for Chemical Image Recognition using Efficient-Net V2 + Transformer