I have pretty simple model

model.compile(optimizer = 'adam',
                    loss=bce_jaccard_loss, metrics=[iou_score])
history = model.fit_generator(training_generator, shuffle =True,
                  epochs=epochs, workers=4, use_multiprocessing=True,
                  validation_data=(x_val, y_val),  
                   verbose = 1)

However after training doesnt have learning rate history, even model doesnt have stored optimizer (no model.optimizer ):

history.history.keys()
dict_keys(['val_loss', 'val_iou_score', 'loss', 'iou_score'])

How to get learning rate history?

PS Sometimes I have it in history.history but now not - what can affect that?

0 Answers