search

piEsposito / blitz-bayesian-deep-learning

A simple and extensible library to create Bayesian Neural Network layers on PyTorch.
GNU General Public License v3.0
918 stars 107 forks source link

Why my loss becomes NAN #76

Closed HDRah closed 3 years ago

HDRah commented 3 years ago

I use BLSTM to make time-series prediction, but the loss becomes NAN after about 40 epoches. Standard LSTM can train my dataset well. Could you know any possible reason? Thank you so much

k-kkk commented 9 months ago

Hello, may I ask how you resolved the issue