google-research/nested-transformer
Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf
Jupyter NotebookApache-2.0
Issues
- 0
This seems like it would be a great option for increasing context window in sequences. Have you tried that yet?
#9 opened by Tylersuard - 3
Regarding GradCAT implementation
#7 opened by rush2406 - 8
Model Converge Problem
#5 opened by khawar-islam - 3
Training hours & Imagenet accuracy
#8 opened by arunos728 - 0
- 3
Discrepancies vs Table A1 in paper
#2 opened by alexander-soare - 6
Found it !!! Hope for Pytorch Implement.
#1 opened by zyxu1996 - 2
About swintransformer ON cifar
#3 opened by ygdr2020 - 2
Swin Transformer on CIFAR
#4 opened by KruC92