search

autonomio / talos

Hyperparameter Experiments with TensorFlow and Keras
https://autonom.io
MIT License
1.62k stars 268 forks source link

early_stopper wrong documentation #321

Closed CodeUser777 closed 5 years ago

CodeUser777 commented 5 years ago

Hi, I just was working on a Project with keras and added talos for hyperparameter opimization. Probably its just my mistake, but I noticed that the documentation (example) of the early_stopper implementation ist wrong.

out = model.fit(x_train, y_train, batch_size=params['batch_size'], epochs=params['epochs'], verbose=0, validation_data=[x_val, y_val], callbacks=early_stopper(params['epochs'], mode='strict')) ```

https://autonomio.github.io/docs_talos/#probabilistic-reduction

correct is to put the early_stopper call in brackets.

out = model.fit(x_train, y_train, batch_size=params['batch_size'], epochs=params['epochs'], verbose=0, validation_data=[x_val, y_val], callbacks=[early_stopper(params['epochs'], mode='strict') ])```

It took me a bit of time to find the problem, that's why I just wanna save someone else some time ;-)

mikkokotila commented 5 years ago

As we make the move to the next LTS version, which starts from v.0.6 (now available in daily-dev branch), part of it involves ensuring that the documentation is 100% in accord with the software. It might take a little bit of time though. To that end, all kinds of contributions will be most welcome.

mikkokotila commented 5 years ago

This is done now, will be in the new docs once it makes to master. Closing here.