a-PyTorch-Tutorial-to-Image-Captioning
a-PyTorch-Tutorial-to-Image-Captioning copied to clipboard
sgrvinod
Dataset not available
I have tried to download the dataset but the link does not redirect anywhere. Maybe you have the dataset in another place or can you upload it to another place to download it?
Thanks for the help.
@Leo-Thomas , yes the link to MSCOCO seems to be broken indeed. Here is how you can get the 2014 dataset
You can run this in a bash script:
mkdir coco
cd coco
mkdir images
cd images
wget -c http://images.cocodataset.org/zips/train2014.zip
wget -c http://images.cocodataset.org/zips/val2014.zip
wget -c http://images.cocodataset.org/zips/test2014.zip
wget -c http://images.cocodataset.org/zips/unlabeled2014.zip
unzip train2014.zip
unzip val2014.zip
unzip test2014.zip
unzip unlabeled2014.zip
rm train2014.zip
rm val2014.zip
rm test2014.zip
rm unlabeled2014.zip
cd ../
wget -c http://images.cocodataset.org/annotations/annotations_trainval2014.zip
wget -c http://images.cocodataset.org/annotations/stuff_annotations_trainval2014.zip
wget -c http://images.cocodataset.org/annotations/image_info_test2014.zip
wget -c http://images.cocodataset.org/annotations/image_info_unlabeled2014.zip
unzip annotations_trainval2014.zip
unzip stuff_annotations_trainval2014.zip
unzip image_info_test2014.zip
unzip image_info_unlabeled2014.zip
rm annotations_trainval2014.zip
rm stuff_annotations_trainval2014.zip
rm image_info_test2014.zip
rm image_info_unlabeled2014.zip
or you can alternatively call it from a jupyter notebook cell using %%bash before the commands, or by adding ! in front of each command.
http://cs.stanford.edu/people/karpathy/deepimagesent/caption_datasets.zip Here is the link of json file.
http://cs.stanford.edu/people/karpathy/deepimagesent/caption_datasets.zip please which folder can i place the downloaded file?
