vision_transformers and awesome-visual-representation-learning-with-transformers
The first is a practical implementation library for building vision transformer models across three tasks, while the second is a curated resource collection documenting the broader ecosystem of transformer-based computer vision approaches—making them complementary rather than competitive, as one provides working code while the other surveys the landscape.
About vision_transformers
sovit-123/vision_transformers
Vision Transformers for image classification, image segmentation, and object detection.
This project helps computer vision practitioners train models to automatically identify objects, classify images, or segment images into meaningful regions. You provide it with images or video data, and it outputs a trained model capable of performing these tasks or shows the detected objects/classifications on your input. It's designed for machine learning engineers, data scientists, and researchers working with visual data.
About awesome-visual-representation-learning-with-transformers
alohays/awesome-visual-representation-learning-with-transformers
Awesome Transformers (self-attention) in Computer Vision
This resource is a curated list of research papers and implementations focused on using Transformer models for various computer vision tasks. It's designed for researchers and practitioners in fields like image analysis, robotics, or autonomous systems who are exploring advanced methods for processing visual data. You can find information on how to use these models for tasks like image classification, object detection, video analysis, and even generating images.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work