search

maxim5 / hyper-engine

Python library for Bayesian hyper-parameters optimization
https://pypi.python.org/pypi/hyperengine
Apache License 2.0
86 stars 22 forks source link

In which method do the system choose hyper-parameters? #17

Open dyj0215 opened 4 years ago

dyj0215 commented 4 years ago

I am just a little confused.

When i changed the neural network setting with concrete parameters, because i just only want to optimize learning rate, the second training will use a new learning rate to train the neural network.

For example, after the first training, i got a final accuracy=0.8172. And then, it will go for a second training with a new learning rate. But the final accuracy maybe be very bad. I thought, after one training, the second training will use the old results to train this model, and then get a better result. But actually, it may get a worse result.

So i want know, how do this system choose the next learning rate? Thank you so much.

maxim5 commented 4 years ago

Your issue is unclear. Please provide the original spec that you used, the output and then changes that you've made.