Optimizers

Table of Contents

• Usage of Optimizers
• Available Optimizers

Usage of Optimizers

An optimizer tries to minimize score returned by loss function adjusting model parameters. Keraflow model requires user to specify the optimizers to configure the model.

model.compile(loss='mse', optimizer='sgd')

Note that sgd stands for SGD. Keraflow uses alias for some build-in optimizers (see below). You could either use the full name or the alias name. Alternatively, You can also pass an optimizer instance to the optimizer argument:

from keraflow.optimizers import SGD

sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mse', optimizer=sgd)

Available Optimizers

• SGD/sgd
• RMSprop/rmsprop
• Adagrad/adagrad
• Adadelta/adadelta
• Adam/adam
• Adamax/adamax