tahmid0007/VisualTransformers
A Pytorch Implementation of the following paper "Visual Transformers: Token-based Image Representation and Processing for Computer Vision"
Python
Issues
- 0
Only 'BasicBlock',not have 'Bottleneck'
#12 opened by miss-rain - 3
Question on token
#7 opened by robeson1010 - 1
Mask shape is not correct
#11 opened by HaoYang0123 - 2
Classification tokens
#9 opened by LexaNagiBator228 - 0
Performances
#10 opened by ssram50 - 0
- 6
some questions
#6 opened by zhenglongjiepheonix - 3
No Documentation!
#5 opened by DebanganThakuria - 3
- 1
Semantic Segmentation
#3 opened by Doubiiu - 3
Hi, regarding the nn1 of ViTResNet:
#2 opened by sdahan12 - 3
Static Tokenization
#1 opened by richardblythman