ra1ph2/Vision-Transformer
Implementation of Vision Transformer from scratch and performance compared to standard CNNs (ResNets) and pre-trained ViT on CIFAR10 and CIFAR100.
Jupyter Notebook
Stargazers
- Aayushk26Mumbai
- ALEX13679173326
- avakanskiUniversity of Idaho
- bhavyagera10
- black0017@The-AI-Summer
- cslxiaoChina
- dairyj0925
- dianhsu@microsoft
- dongwikiBeiJing
- eremo2002
- eternaldolphin
- Fatflower
- fly51flyPRIS
- futty12
- happycaoyueHarbin Institute of Technology
- HiroForYouLima, Peru
- iliasprc@The-AI-Summer
- imirzadehUnited States
- kodacheung
- konradhartwig
- mandelbrot-walker
- Mooler0410
- nakashima-kodai
- paulwong16University of Alberta
- PengPeixi
- ra1ph2
- rishabhlumiqLumiq
- Roxbili
- santyelegyRutgers University
- shang-jun123
- stjordanisGreece
- VCCIV
- vismit2000Goldman Sachs
- woshidandanBeijing University of Posts and Telecommunications
- xmxxiong
- yifanc96NYU