LeapLabTHU/DAT
Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention
This project provides advanced computer vision models that efficiently classify images. It takes raw image data and outputs accurate classifications of objects within those images, improving upon standard methods by focusing on key visual areas. Researchers and machine learning engineers working on image analysis and recognition tasks would find this particularly useful.
925 stars. No commits in the last 6 months.
Use this if you need to perform image classification with high accuracy and efficiency, especially in scenarios where distinguishing fine details or complex scenes is crucial.
Not ideal if your primary task is object detection or image segmentation, as dedicated versions of this technology exist for those specific applications.
Stars
925
Forks
84
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LeapLabTHU/DAT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...