LSTM-Neural-Network-for-Time-Series-Prediction Does this code set the learning rate？when i use my own dataset，the loss becomes nan and i want to decrease the learning-rate but i cant find it

Does this code set the learning rate？when i use my own dataset，the loss becomes nan and i want to decrease the learning-rate but i cant find it

Open zhangzhang-vvv opened this issue 4 years ago • 3 comments

Mar 28 '20 13:03 zhangzhang-vvv

No, it takes the defaulf one by adam. If you want to change it, add it in the config.json and change it in the model.py

Aug 05 '20 10:08 VincieD

Change the LR by below code: K.set_value(model.optimizer.lr, 0.0001)

May 03 '21 10:05 dongdongrj

Also faced similar issues, but then realized the preprocessing work is insufficient, and null values in any part of your dataset can break the model, thus giving you nan losses.

Jun 10 '21 20:06 xFireBerg

LSTM-Neural-Network-for-Time-Series-Prediction LSTM-Neural-Network-for-Time-Series-Prediction copied to clipboard

Does this code set the learning rate？when i use my own dataset，the loss becomes nan and i want to decrease the learning-rate but i cant find it

LSTM-Neural-Network-for-Time-Series-Prediction
LSTM-Neural-Network-for-Time-Series-Prediction copied to clipboard