python main.py sru: trainning RNNs with fixed parameters.
python tune_params.py sru : tuning hyper parameters with hyperopt.
Choose your model from [sru, gru, lstm]
If you need more information, please run python tune_params.py --help.
notes
I choose Adam for optimization, though SGD is used in the paper. (It might converge faster)
weight_decay is used. (The paper doesn't refer to it)
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].