Ken Luo

Sorry if I missed anything, but I wonder if there is any reason why switch was not used for maxunpooling as the original paper stated? Thanks,

vgg16 has no dropout

1

I notice there is no dropout in the vgg16 code whereas dropout was used in the original paper. I wonder if there is a reason for removing it and whether...

Trained model weights

2

Thanks for making the code available! I was wondering, apart from the Resnet-18 checkpoint you mentioned in README (the link seems failing by the way), are any of the model...

I may have missed something but it seems in the `process_data.py` file you have only created input features as unigrams but the original paper uses both unigram and bigrams. Also...

Thank you for the helpful examples! I have a question regarding: https://github.com/huggingface/notebooks/blob/main/examples/text_classification.ipynb Specifically, under the `Hyperparameter search` section, I wonder if it is expected behavior that the model is initialized...