ImageNet Preparation for PyTorch torch vision.datasets.imagenet

imagenet.sh

#!/bin/bash
#
# These files should exist:
# $ ls
# ILSVRC2012_devkit_t12.tar.gz  ILSVRC2012_img_train.tar  ILSVRC2012_img_val.tar
#
# When this script is finished:
# $ ls
# imagenet  ILSVRC2012_devkit_t12.tar.gz  ILSVRC2012_img_train.tar  ILSVRC2012_img_val.tar
# $ ls imagenet
# ILSVRC2012_devkit_t12.tar.gz  train  val

mkdir imagenet && cd imagenet
cp ../ILSVRC2012_devkit_t12.tar.gz .

# Extract the training data
mkdir train && cd train
tar -xvf ../../ILSVRC2012_img_train.tar
find . -name "*.tar" | while read NAME ; do mkdir -p "${NAME%.tar}"; tar -xvf "${NAME}" -C "${NAME%.tar}"; rm -f "${NAME}"; done
cd ..

# Extract the validation data and move images to subfolders:
mkdir val && cd val
tar -xvf ../../ILSVRC2012_img_val.tar
wget -qO- <https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh> | bash