Performance comparison to baseline models

EdGENetworks / attention-networks-for-classification

Hierarchical Attention Networks for Document Classification in PyTorch

603 stars 132 forks source link

Performance comparison to baseline models #1

Closed bkj closed 7 years ago

bkj commented 7 years ago

I was wondering whether you could add accuracy numbers to the notebook/README rather than just the loss numbers. Also, do you know the accuracy/loss values for a baseline network? Does the HAN outperform?

Thanks!

Sandeep42 commented 7 years ago

I am still experimenting with the model, and I did manage to include the bias term that was missing. I probably won't have time to cross-validate all their results, but I will do that on one data set and update here very soon. Please feel free to report any testings that you might have done!