Closed ajtejankar closed 3 years ago
Hi @chigur,
I'm looking into this now, and will get back to you shortly! Have you also experienced this issue when running the 10% models?
Hi @MidoAssran,
I did not check the 10% models. Let me try them.
Thank You Ajinkya Tejankar
Hi @MidoAssran,
I was able to reproduce the 10% NN accuracies for all the checkpoints.
Thank You Ajinkya Tejankar
Thanks for letting me know @chigur
So I discovered that the issue was that the 1% NN results were reported using
python snn_eval.py
--model-name resnet50 --use-pred
--pretrained $path_to_pretrained_model
--unlabeled_frac 0.9
--root-path $path_to_root_datasets_directory
--image-folder $image_directory_inside_root_path
--dataset-name $one_of:[imagenet_fine_tune, cifar10_fine_tune]
instead of
python snn_eval.py
--model-name resnet50 --use-pred
--pretrained $path_to_pretrained_model
--unlabeled_frac 0.99
--root-path $path_to_root_datasets_directory
--image-folder $image_directory_inside_root_path
--dataset-name $one_of:[imagenet_fine_tune, cifar10_fine_tune]
The first one uses 10% of imagenet train embeddings for the nearest neighbours evaluation, whereas the second one uses 1% of imagenet train embeddings for nearest neighbours evaluation. The correct one is the second one (similar to the one you used).
I checked the 10% NN results and those seem fine for me as well, and also the 1% and 10% fine-tuned numbers, and those also seem fine, so the issue was localized to the size of the lookup table for evaluating the 1% NN models. Thanks again for noticing this, I will update the table with the correct numbers for the 1% NN models.
I'll close this issue now, but let me know if you have any other questions.
Great! I guess the numbers in the paper are slightly off as well.
yes, the 1% NN need to be changed :) that's actually what I mean by updating the table
Hi,
I am interested in using the pretrained models, but I could not reproduce the numbers in the table. I downloaded the 1% checkpoints and ran the soft nearest neighbor evaluation on 1% ImageNet for all 3 checkpoints (100, 200, and 300 epochs). Here are the numbers that I got:
Here's the command that I used:
Here's the output of the above command:
Thank You Ajinkya Tejankar