TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi
TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi copied to clipboard
Published
20 hours ago •
EdjeElectronics
EdjeElectronics
Using a different optimizer in pipeline config file
trafficstars
As far as I understand, I can only use the optimizers that are defined in optimizer.proto which are namely RMSProp, Adam and Momentum. And I can also tamper with their learning rate and other such params.
How do I use some meta-heuristicoptimizer in the config file? Because I could probably use some library for that but how do I about using config file? And if I can't, do i have to scrape the whole config file idea and do it the usual way?
Any help would be appreciated. Thank you
