brando90 / pytorch-meta-dataset

A non-official 100% PyTorch implementation of META-DATASET benchmark for few-shot classification
0 stars 0 forks source link

sanity checks for image net? #21

Closed brando90 closed 1 year ago

brando90 commented 1 year ago

https://github.com/google-research/meta-dataset/issues/105

I was running

ls $MDS_DATA_PATH/ILSVRC2012_img_train/
ls $MDS_DATA_PATH/ILSVRC2012_img_train/ | grep -c .tar
# 5620
ls $MDS_DATA_PATH/ILSVRC2012_img_train/ -1 | grep -v "\.tar$" | wc -l
# 5622

and got those numbers in the comment. Are those the expect number of files for imagenet? Seems rather small?

brando90 commented 1 year ago

lets consolidate all response to this here @patricks-lab https://github.com/brando90/pytorch-meta-dataset/issues/5