Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space
This is the official repository to the CVPR 2022 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space” This repo is based on the training code in Deit and the tools in timm.
Getting Started
You will need Python 3.8 and the packages specified in requirements.txt.
We recommend setting up a virtual environment with pip
and installing the packages there.
Install packages with:
$ pip install -r requirements.txt
Data preparation
The layout of Imagenet data:
/path/to/imagenet/
train/
class1/
img1.jpeg
class2/