BR-IDL/PaddleViT
A collection of vision transformer and MLP architectures for computer vision tasks including classification, object detection, semantic segmentation, and GAN, built on PaddlePaddle.
Not currently ranked — collecting fresh signals.
star history
PaddleViT provides implementations of state-of-the-art Visual Transformers and MLP models for computer vision tasks such as image classification, object detection, semantic segmentation, and generative adversarial networks. The library integrates with the PaddlePaddle deep learning framework and includes model architectures, training/validation scripts, data augmentation utilities, and pretrained weights for fine-tuning.
Frequently asked
- What is BR-IDL/PaddleViT?
- A collection of vision transformer and MLP architectures for computer vision tasks including classification, object detection, semantic segmentation, and GAN, built on PaddlePaddle.
- Is PaddleViT open source?
- Yes — BR-IDL/PaddleViT is open source, released under the Apache-2.0 license.
- What language is PaddleViT written in?
- BR-IDL/PaddleViT is primarily written in Python.
- How popular is PaddleViT?
- BR-IDL/PaddleViT has 1.2k stars on GitHub.
- Where can I find PaddleViT?
- BR-IDL/PaddleViT is on GitHub at https://github.com/BR-IDL/PaddleViT.