Dataset Version Used

[odb2]

I have a question with the dataset used in this project I read from certain sites and including Kaggle there is Imagenet - ILSVRC2012 dataset which is around ~150Gb and has 1000 classes. But I also see from the Imagenet site that it obtains ~21,000 classes. Therefore, is the training in this paper done on the entire Imagenet dataset ~21,000 classes or on the smaller dataset of 1000 classes?

Also, do you think running your resnet_upscaled_static.sh script will provide similar results if I feed the dataset which obtains 1000 classes?

Also awesome paper btw!

[kaix90]

Thanks very much for your question. We use ILSVRC2012 with ~150Gb and 1000 classes.

[odb2]

Thanks! One additional instruction that might help others would be when downloading imagenet the validation files do not come organized in folders like the training folder I had to run this script https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh which I found through https://docs.nvidia.com/deeplearning/dali/archives/dali_08_beta/dali-developer-guide/docs/examples/pytorch/resnet50/pytorch-resnet50.html to get them organized into folders.

[suvadeepbanerjee]

@odbarragan Thank you. This is super important as the _find_classes method searches directories and in the absence of the directory arrangement, the code fails to work.