transformer-in-transformer
performer-pytorch
| transformer-in-transformer | performer-pytorch | |
|---|---|---|
| 1 | 2 | |
| 291 | 1,055 | |
| - | - | |
| 1.8 | 1.8 | |
| over 2 years ago | over 2 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.
transformer-in-transformer
-
“Transformer in Transformer” paper explained!
A thirdparty implementation of " Transformer in Transformer": https://github.com/lucidrains/transformer-in-transformer
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)
What are some alternatives?
noah-research - Noah Research
long-range-arena - Long Range Arena for Benchmarking Efficient Transformers
Perceiver - Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow
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"
reformer-pytorch - Reformer, the efficient Transformer, 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
deep-implicit-attention - Implementation of deep implicit attention in PyTorch
scenic - Scenic: A Jax Library for Computer Vision Research and Beyond
TimeSformer-pytorch - Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
x-transformers - A simple but complete full-attention transformer with a set of promising experimental features from various papers
graphtransformer - Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to Graphs", DLG-AAAI'21.
CoCa-pytorch - Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch