Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

why # of image classes are more than 1000? #10

Open
spaul13 opened this issue Jun 8, 2020 · 3 comments
Open

why # of image classes are more than 1000? #10

spaul13 opened this issue Jun 8, 2020 · 3 comments

Comments

@spaul13
Copy link

spaul13 commented Jun 8, 2020

can anyone please tell me why there are more than 1000 classes listed in .csv file. what I know that imagenet has 1000 classes only on which torchvision.models resnet101, densenet161 and other models are trained on.

@CMCDragonkai
Copy link

Imagenet actually has 21841 classes ("nouns" from wordnet). However the ILSVRC competitions use a trimmed 1000 class set. Each year it can be different. So the 2017 competition used: http://image-net.org/challenges/LSVRC/2017/#loc

Note that imagenet classes are imbalanced. And some of the classes overlap. So the trimmed classes were picked not to overlap and probably have the same number of images per class.

@washraf
Copy link

washraf commented Oct 27, 2020

How can I use this tool to download the classes as used in the ImageNet competition (1000 class)

@FinAminToastCrunch
Copy link

Any update on this?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants