(DeiT)Training data-efficient image transformers & distillation through attention
Published:
Training data-efficient image transformers & distillation through attention.
Yuxi Lu
Research for Artificial Intelligence Algorithm.
- Fuzhou, Fujian, China
- Github
- Google Scholar
Hyper Parameter Optimization
less than 1 minute read
Published:
Neural network Hyper Parameter Optimization.
Handwritten ST-GCN
less than 1 minute read
Published:
Handwritten the ST-GCN.
ST-GCN
less than 1 minute read
Published:
ST-GCN structure.
Realize the Model Soup
less than 1 minute read
Published:
Realize the Model Soup.