This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
Efficient vision foundation models for high-resolution generation and perception.
The main features of mit-han-lab/efficientvit are: Efficient Vision Architectures, Efficient Vision Transformers.
Open-source alternatives to mit-han-lab/efficientvit include: apple/ml-fastvit — This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer… br-idl/paddlevit — :robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+. changlin31/ds-net. changsn/stvit-r. chenglin-yang/lvt. ackesnal/gtp-vit.
