microsoft/Cream
Collection of neural architecture search methods and efficient Vision Transformer models for visual recognition, including distillation and compression techniques.
Not currently ranked — collecting fresh signals.
star history
This repository aggregates Microsoft’s research on automated neural architecture design and search. It includes multiple NAS algorithms for discovering efficient transformer architectures and techniques for compressing vision models via weight multiplexing, knowledge distillation, and affinity mimicking. The work spans methods like AutoFormer, CDARTS, TinyViT, and MiniViT, providing implementations for training, searching, and compressing vision transformers.
Frequently asked
- What is microsoft/Cream?
- Collection of neural architecture search methods and efficient Vision Transformer models for visual recognition, including distillation and compression techniques.
- Is Cream open source?
- Yes — microsoft/Cream is open source, released under the MIT license.
- What language is Cream written in?
- microsoft/Cream is primarily written in Python.
- How popular is Cream?
- microsoft/Cream has 1.8k stars on GitHub.
- Where can I find Cream?
- microsoft/Cream is on GitHub at https://github.com/microsoft/Cream.