Related tutorials:
Use callbacks to trigger the end of training cycles
Code:
class myCallback(tf.keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs={}):
if(logs.get('accuracy')>0.9):
print("\nReached 90% accuracy so cancelling training!")
self.model.stop_training = True
Imports:
callbacks = myCallback()
#example usage:
model.fit(value_a, value_b, epochs=500, callbacks=[callbacks])
Tensorthings 