index = list(range(testSize * NUMBER_OF_CLASS))
random.seed(660)
random.shuffle(index)
x_val = x_val[index]
y_val = y_val[index]
model_weights = "./model/aux_model"
checkpoint = ModelCheckpoint(model_weights,
monitor='val_loss',
verbose=0,
save_best_only=True,
mode='min',
save_weights_only=True)
a_model = fed_learn.create_model((32, 32, 3),
NUMBER_OF_CLASS,
init_with_imagenet=False,
learning_rate=0.01)
plateau = ReduceLROnPlateau(monitor='val_loss',
factor=0.5,
patience=5,
verbose=1,
min_delta=1e-4,
mode='min')
early_stopping = EarlyStopping(monitor="val_loss", patience=15)
y_train = utils.to_categorical(y_train, NUMBER_OF_CLASS)
print(a_model.summary())
a_model.fit(x_share,
y_share,
validation_data=(x_val, y_val),
epochs=5000,
def model_fn():
return fed_learn.create_model((32, 32, 3),
NUMBER_OF_CLASS,
init_with_imagenet=True,
learning_rate=args.learning_rate)
def model_fn():
return fed_learn.create_model((32, 32, 3), 10, init_with_imagenet=False, learning_rate=args.learning_rate)