berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
This is a tool for developers who are building advanced computer vision applications. It provides a robust and efficient 'backbone' for tasks like identifying objects in images or understanding different regions in a scene. You give it image data, and it processes it to extract powerful visual features, which can then be used for tasks such as categorizing images or detecting specific items.
859 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer or researcher implementing custom computer vision models and need a high-performance, flexible vision transformer architecture as a core component.
Not ideal if you are an end-user looking for a ready-to-use application for image analysis, as this is a foundational development library.
Stars
859
Forks
131
Language
Python
License
MIT
Category
Last pushed
Mar 29, 2021
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/berniwal/swin-transformer-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
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...
sniklaus/pytorch-pwc
a reimplementation of PWC-Net in PyTorch that matches the official Caffe version