How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
This is a collection of our NAS and Vision Transformer work.
The main features of microsoft/cream are: Efficient Vision Architectures, Efficient Vision Transformers, Hybrid Vision Architectures, Vision Backbones and Classification, Vision Transformers, Model Compression.
Projects with overlapping indexed features include: ibm/crossvit — Official implementation of CrossViT. https://arxiv.org/abs/2103.14899. raoyongming/dynamicvit — This repository contains PyTorch implementation for DynamicViT (NeurIPS 2021). facebookresearch/deit — DeiT is a PyTorch vision transformer framework designed for image classification. It implements a transformer-based… facebookresearch/levit — LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference. facebookresearch/convit — This repository contains PyTorch code for ConViT. It builds on code from the Data-Efficient Vision Transformer and… danczs/visformer — This is a pytorch implementation for the Visformer models. This project is based on the training code in DeiT and the…
This repository contains PyTorch implementation for DynamicViT (NeurIPS 2021).
DeiT is a PyTorch vision transformer framework designed for image classification. It implements a transformer-based architecture that processes images as sequences of flattened patches using self-attention layers and position-aware sequence modeling instead of convolutional filters. The project focuses on data-efficient training through a knowledge distillation framework. This system allows a student model to mimic the soft labels of a high-performance teacher model to improve accuracy and generalization, particularly when training on smaller datasets. The library covers the full development
This is a pytorch implementation for the Visformer models. This project is based on the training code in DeiT and the tools in timm.
