search

Romit-Maulik / CAE_LSTM_ROMS

Supporting code for "Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders"
19 stars 11 forks source link

There is no code for the first case training, can you please provide it? #1

Open JoeroyaI opened 2 years ago

JoeroyaI commented 2 years ago

There is no code for the first case training, can you please provide it?

Romit-Maulik commented 2 years ago

Are you referring to this? https://github.com/Romit-Maulik/CAE_LSTM_ROMS/blob/main/Burgers_Equations/AE_LSTM_MP.ipynb

JoeroyaI commented 2 years ago

yes，how can we get the “best_weights_ae.h5” in this notebook I mean. Is the procedure for the training of the first case not in it? Thank you very much for your answer! image

JoeroyaI commented 2 years ago

My email is qiaolongye@gmail.com,I wanna learn it carefully,3ku very much.

Romit-Maulik commented 2 years ago

So those weights can be generated if you set mode = 'train' as you see here image The pretrained weights are also available here: https://github.com/Romit-Maulik/CAE_LSTM_ROMS/blob/main/Burgers_Equations/best_weights_ae.h5

JoeroyaI commented 2 years ago

3ku very much