saving the trained model for future use -

[vijaymanikandan]

Thanks for posting your code, I played with it to understand LSTM implementation. I just have a quick question regarding saving the models for later use. Right now, when I run train.py, I can see the model getting trained and I see some outputs. But is there a way to save the model to file and later use it to retrain/predict on future data? I tried using pickle but I get an error saying maximum recursion reached. Please post your thoughts.

Thanks!

[lmqs]

I also need to save the trained model, I tried to save "NTWK" but gives serialization error: maximum recursion depth exceeded. Has anyone experienced this? thanks

[guduxingzou]

hello do you have done that,save/predict the model? @vijaymanikandan @lucianaqueiroz098

[rakeshvar]

I don't plan to. As it is not meant to be a full-fledged product. Only a proof of concept. It is a very bare bones implementation, not an end-to-end product. May be someone has it on a fork?

[lmqs]

I think saving the outputs required function "tester": the layer 2 and layer 1 work, @rakeshvar can confirm this?

[guduxingzou]

the predict I think to use the teser function .

I get this repo: https://github.com/mosessoh/CNN-LSTM-Caption-Generator @rakeshvar Can this repo handle this digit recognition ?