search

karpathy / neuraltalk2

Efficient Image Captioning code in Torch, runs on GPU
5.5k stars 1.26k forks source link

COCO images and Torch's image reader #13

Open FabHan opened 8 years ago

FabHan commented 8 years ago

I tried to run your pretrained model on COCO validation set. It didn't work and I figured out that some images in COCO are png, although they have .jpg extension. This confuses Torch's image reader: not a JPEG file. OpenCV doesn't have this problem because it detects the image format using the header, not the filename.

Did you encounter this when working on COCO data? If so, what processing did you do?

karpathy commented 8 years ago

Wow, that's painful! I didn't realize or encounter this, because preprocessing is done in Python. I'm using torch load for some files (e.g. mscoco test set files), but there it seemed to work fine, probably no corruptions.

soumith commented 8 years ago

ouch that's painful indeed. I can fix up the torch image loader in the next 7 days (ironically the COCO deadline is tonight). We already have the torch loader do this for Memory images (i.e. look at header, rather than file extension), we haven't done it for disk images.

gqcao commented 8 years ago

@FabHan Can you use Imagemagick to convert all png images to jpegs, and then do the work?

FabHan commented 8 years ago

I don't know all png images in the dataset. I certainly could write a script to find and convert but well, I just haven't done it yet.

cdluminate commented 8 years ago

please try my image checker in https://github.com/CDLuminate/cocofetch .

When I'm downloading COCO dataset I find that flicker just returns a png (saying "picture not available anymore") instead of the original jpg when the picture is no longer valid. Download it from mscoco.org directly. And my scripts may help you do that.

See file: check_jpeg.py