0
$\begingroup$

If I'd previously trained a model and saved the whole training session (using TensorFlow tf.train.Saver.save()), and then later restored the session (using TensorFlow tf.train.Saver.restore()) but then wanted to train using different hyperparameters (batch/mini-batch and learning rate), then I assume the optimizer would need to be reset. Is that the only part of the previous session that would need to reset?

$\endgroup$
1
$\begingroup$

Yes as far as I know you only need to reset the optimizer.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.