Hierarchical-attention-networks-pytorch and tf-han

These two tools are competitors, as both implement the Hierarchical Attention Networks model for document classification, but tool A uses PyTorch while tool B uses TensorFlow.

tf-han
29
Experimental
Maintenance 0/25
Adoption 10/25
Maturity 8/25
Community 24/25
Maintenance 0/25
Adoption 5/25
Maturity 9/25
Community 15/25
Stars: 406
Forks: 107
Downloads:
Commits (30d): 0
Language: Python
License:
Stars: 9
Forks: 5
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: Apache-2.0
No License Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About Hierarchical-attention-networks-pytorch

vietnh1009/Hierarchical-attention-networks-pytorch

Hierarchical Attention Networks for document classification

Implements two-level attention mechanisms at word and sentence levels to capture document structure, with GloVe word embeddings (50-300d) initialized in the embedding layer rather than default random initialization. Built on PyTorch with early stopping regularization and TensorBoard integration for training visualization. Includes a web demo interface and pre-trained models evaluated across eight datasets (AG News, DBPedia, Yelp, Amazon, Yahoo Answers) with configurable batch size, learning rate, and embedding dimensions.

About tf-han

shengc/tf-han

TensorFlow Implementation For [Hierarchical Attention Networks for Document Classification](http://www.cs.cmu.edu/~./hovy/papers/16HLT-hierarchical-attention-networks.pdf)

Scores updated daily from GitHub, PyPI, and npm data. How scores work