whai362/PVT
A Pyramid Vision Transformer implementation providing backbone models for image classification, object detection, and semantic segmentation.
Not currently ranked — collecting fresh signals.
star history
This repository contains the official implementation of PVTv1 and PVTv2, transformer-based architectures designed as drop-in backbones for various vision tasks. The models achieve strong results on ImageNet-1K classification, COCO object detection, and semantic segmentation benchmarks. PVTv2 improves upon the original PVT and compares favorably to alternatives like Swin Transformer.
Frequently asked
- What is whai362/PVT?
- A Pyramid Vision Transformer implementation providing backbone models for image classification, object detection, and semantic segmentation.
- Is PVT open source?
- Yes — whai362/PVT is open source, released under the Apache-2.0 license.
- What language is PVT written in?
- whai362/PVT is primarily written in Python.
- How popular is PVT?
- whai362/PVT has 1.9k stars on GitHub.
- Where can I find PVT?
- whai362/PVT is on GitHub at https://github.com/whai362/PVT.