cmsflash / efficient-attention
An implementation of the efficient attention module.
☆283Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for efficient-attention
- Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision☆209Updated 3 years ago
- Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorc…☆300Updated 2 years ago
- [ICLR'22 Oral] Implementation of "CycleMLP: A MLP-like Architecture for Dense Prediction"☆280Updated 2 years ago
- Implementation of Axial attention - attending to multi-dimensional data efficiently☆351Updated 3 years ago
- Implementation of Pixel-level Contrastive Learning, proposed in the paper "Propagate Yourself", in Pytorch☆252Updated 3 years ago
- ☆189Updated last year
- ☆239Updated 2 years ago
- Implementation of Linformer for Pytorch☆255Updated 10 months ago
- Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones☆199Updated 3 years ago
- [NeurIPS 2021 Spotlight] Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"☆544Updated 2 years ago
- Fully featured implementation of Routing Transformer☆284Updated 3 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆222Updated 2 years ago
- Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.☆546Updated 10 months ago
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆179Updated last year
- MLP-Like Vision Permutator for Visual Recognition (PyTorch)☆190Updated 2 years ago
- Implementation of ConvMixer for "Patches Are All You Need? 🤷"☆1,062Updated last year
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆695Updated 6 months ago
- Code repository of the paper "Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN" https://arxiv.org/abs…☆180Updated last year
- A PyTorch implementation of the 1d and 2d Sinusoidal positional encoding/embedding.☆251Updated 3 years ago
- [ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?☆325Updated 2 years ago
- Learning Rate Warmup in PyTorch☆393Updated this week
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆251Updated 3 years ago
- ☆195Updated 3 months ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆253Updated 3 years ago
- A Pytorch implementation of Global Self-Attention Network, a fully-attention backbone for vision tasks☆92Updated 3 years ago
- Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)☆480Updated 3 years ago
- A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.☆136Updated 2 years ago
- An All-MLP solution for Vision, from Google AI☆1,001Updated last month
- Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, de…☆97Updated 2 years ago
- [NeurIPS 2021] [T-PAMI] Global Filter Networks for Image Classification☆445Updated last year