PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)
MIT License
Statistics for this project are still being loaded, please check back later.
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose E...
TensorFlow 2.X reimplementation of CvT: Introducing Convolutions to Vision Transformers, Haiping ...
Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which i...
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, e...
Reformer, the efficient Transformer, in Pytorch
Collection of SOTA efficient computer vision models for embedded applications, with pre-trained w...
solo-learn: a library of self-supervised methods for visual representation learning powered by Py...
A flexible package for multimodal-deep-learning to combine tabular data with text and images usin...
Train high-quality text-to-image diffusion models in a data & compute efficient manner
PyTorch reimplementation of FlexiViT: One Model for All Patch Sizes
PyTorch and TensorFlow/Keras image models with automatic weight conversions and equal API/impleme...