We provide installation instructions for ImageNet classification experiments here.
Create a new conda virtual environment
conda create -n ws python=3.8 -y
conda activate ws
Install Pytorch>=1.8.0, torchvision>=0.9.0 following official instructions. For example:
pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
Clone this repo and install required packages:
git clone https://github.com/anonymous-wivwauyg/weight-selection.git
pip install timm==0.6.12 tensorboardX six
The results in the paper are produced with torch==1.8.0+cu111 torchvision==0.9.0+cu111 timm==0.4.12.
Download the ImageNet-1K classification dataset and structure the data as follows:
/path/to/imagenet-1k/
train/
class1/
img1.jpeg
class2/
img2.jpeg
val/
class1/
img3.jpeg
class2/
img4.jpeg