performer-pytorch
deep-implicit-attention
performer-pytorch | deep-implicit-attention | |
---|---|---|
2 | 1 | |
1,055 | 61 | |
- | - | |
1.8 | 0.0 | |
over 2 years ago | almost 3 years ago | |
Python | Python | |
MIT License | MIT License |
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.
performer-pytorch
-
[R] Rotary Positional Embeddings - a new relative positional embedding for Transformers that significantly improves convergence (20-30%) and works for both regular and efficient attention
Performer is the best linear attention variant, but linear attention is just one type of efficient attention solution. I have rotary embeddings already in the repo https://github.com/lucidrains/performer-pytorch and you can witness this phenomenon yourself by toggling it on / off
-
Why has Google's Performer model not replaced traditional softmax attention?
Here's an PyTorch implementation if you want to play around with it: lucidrains/performer-pytorch: An implementation of Performer, a linear attention-based transformer, in Pytorch (github.com)
deep-implicit-attention
-
[P] Deep Implicit Attention: A Mean-Field Theory Perspective on Attention Mechanisms
Code: https://github.com/mcbal/deep-implicit-attention
What are some alternatives?
long-range-arena - Long Range Arena for Benchmarking Efficient Transformers
TimeSformer-pytorch - Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
Perceiver - Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow
soundstorm-pytorch - Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
memory-efficient-attention-pytorch - Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
x-transformers - A simple but complete full-attention transformer with a set of promising experimental features from various papers
reformer-pytorch - Reformer, the efficient Transformer, in Pytorch
afem - Implementation of approximate free-energy minimization in PyTorch
vit-pytorch - Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
DALLE-pytorch - Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
scenic - Scenic: A Jax Library for Computer Vision Research and Beyond
spin-model-transformers - Physics-inspired transformer modules based on mean-field dynamics of vector-spin models in JAX