History

D-X-Y 180702ab8e update missing data of GDAS		2019-09-28 20:10:23 +10:00
..
data	update missing data of GDAS	2019-09-28 20:10:23 +10:00
logs	update missing data of GDAS	2019-09-28 20:10:23 +10:00
classes.txt	update missing data of GDAS	2019-09-28 20:10:23 +10:00
compress.py	update missing data of GDAS	2019-09-28 20:10:23 +10:00
decompress.py	update missing data of GDAS	2019-09-28 20:10:23 +10:00
GDAS.pdf	update missing data of GDAS	2019-09-28 20:10:23 +10:00
GDAS.png	update missing data of GDAS	2019-09-28 20:10:23 +10:00
Get-PTB-WT2.sh	update missing data of GDAS	2019-09-28 20:10:23 +10:00
ImageNet-100.txt	update missing data of GDAS	2019-09-28 20:10:23 +10:00
imagenet-results.png	update missing data of GDAS	2019-09-28 20:10:23 +10:00
load_data_CUHK-PEDES.py	update missing data of GDAS	2019-09-28 20:10:23 +10:00
ps_mem.py	update missing data of GDAS	2019-09-28 20:10:23 +10:00
README.md	update missing data of GDAS	2019-09-28 20:10:23 +10:00
show-queue.sh	update missing data of GDAS	2019-09-28 20:10:23 +10:00
split-imagenet.py	update missing data of GDAS	2019-09-28 20:10:23 +10:00
tiny-imagenet.py	update missing data of GDAS	2019-09-28 20:10:23 +10:00

README.md

ImageNet

The class names of ImageNet-1K are in classes.txt.

A 100-class subset of ImageNet-1K : ImageNet-100

The class names of ImageNet-100 are in ImageNet-100.txt.

Run python split-imagenet.py will automatically create ImageNet-100 based on the data of ImageNet-1K. By default, we assume the data of ImageNet-1K locates at ~/.torch/ILSVRC2012. If your data is in a different location, you need to modify line-19 and line-20 in split-imagenet.py.

Tiny-ImageNet

The official website is here. Please run python tiny-imagenet.py to generate the correct format of Tiny ImageNet for training.

PTB and WT2

Run bash Get-PTB-WT2.sh to download the data.