Questa pagina è stata tradotta dall'API Cloud Translation.
Switch to English

Scrivi i tuoi callback

Visualizza su TensorFlow.org Esegui in Google Colab Visualizza sorgente su GitHub Scarica il quaderno

introduzione

Un callback è un potente strumento per personalizzare il comportamento di un modello di Keras durante l'allenamento, la valutazione o l'inferenza. Gli esempi includono tf.keras.callbacks.TensorBoard per visualizzare i progressi ei risultati dell'allenamento con TensorBoard o tf.keras.callbacks.ModelCheckpoint per salvare periodicamente il modello durante l'allenamento.

In questa guida imparerai cos'è un callback di Keras, cosa può fare e come puoi crearne uno tuo. Per iniziare, forniamo alcune demo di semplici applicazioni di callback.

Impostare

 import tensorflow as tf
from tensorflow import keras
 

Panoramica dei callback di Keras

Tutti i callback subclassano la classe keras.callbacks.Callback e sovrascrivono una serie di metodi chiamati in varie fasi di addestramento, test e previsione. I callback sono utili per avere una visione degli stati interni e delle statistiche del modello durante l'allenamento.

È possibile passare un elenco di callback (come callbacks dell'argomento parola chiave) ai seguenti metodi del modello:

Una panoramica dei metodi di callback

Metodi globali

on_(train|test|predict)_begin(self, logs=None)

Chiamato all'inizio di fit / evaluate / predict .

on_(train|test|predict)_end(self, logs=None)

Chiamato alla fine di fit / evaluate / predict .

Metodi a livello di batch per addestramento / test / previsione

on_(train|test|predict)_batch_begin(self, batch, logs=None)

Chiamato subito prima dell'elaborazione di un batch durante l'addestramento / test / previsione.

on_(train|test|predict)_batch_end(self, batch, logs=None)

Chiamato al termine della formazione / test / previsione di un batch. All'interno di questo metodo, i logs sono un dict contenente i risultati delle metriche.

Metodi a livello di epoca (solo formazione)

on_epoch_begin(self, epoch, logs=None)

Chiamato all'inizio di un'epoca durante l'allenamento.

on_epoch_end(self, epoch, logs=None)

Chiamato alla fine di un'epoca durante l'allenamento.

Un esempio di base

Diamo un'occhiata a un esempio concreto. Per iniziare, importiamo tensorflow e definiamo un semplice modello di Keras sequenziali:

 # Define the Keras model to add callbacks to
def get_model():
    model = keras.Sequential()
    model.add(keras.layers.Dense(1, input_dim=784))
    model.compile(
        optimizer=keras.optimizers.RMSprop(learning_rate=0.1),
        loss="mean_squared_error",
        metrics=["mean_absolute_error"],
    )
    return model

 

Quindi, carica i dati MNIST per l'addestramento e il test dall'API dei set di dati di Keras:

 # Load example MNIST data and pre-process it
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
x_train = x_train.reshape(-1, 784).astype("float32") / 255.0
x_test = x_test.reshape(-1, 784).astype("float32") / 255.0

# Limit the data to 1000 samples
x_train = x_train[:1000]
y_train = y_train[:1000]
x_test = x_test[:1000]
y_test = y_test[:1000]
 
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
11493376/11490434 [==============================] - 0s 0us/step

Ora, definisci un semplice callback personalizzato che registra:

  • Quando l' fit / evaluate / predict inizia e termina
  • Quando ogni epoca inizia e finisce
  • Quando ogni lotto di allenamento inizia e termina
  • Quando ogni lotto di valutazione (test) inizia e termina
  • Quando ogni batch di inferenza (previsione) inizia e termina
 class CustomCallback(keras.callbacks.Callback):
    def on_train_begin(self, logs=None):
        keys = list(logs.keys())
        print("Starting training; got log keys: {}".format(keys))

    def on_train_end(self, logs=None):
        keys = list(logs.keys())
        print("Stop training; got log keys: {}".format(keys))

    def on_epoch_begin(self, epoch, logs=None):
        keys = list(logs.keys())
        print("Start epoch {} of training; got log keys: {}".format(epoch, keys))

    def on_epoch_end(self, epoch, logs=None):
        keys = list(logs.keys())
        print("End epoch {} of training; got log keys: {}".format(epoch, keys))

    def on_test_begin(self, logs=None):
        keys = list(logs.keys())
        print("Start testing; got log keys: {}".format(keys))

    def on_test_end(self, logs=None):
        keys = list(logs.keys())
        print("Stop testing; got log keys: {}".format(keys))

    def on_predict_begin(self, logs=None):
        keys = list(logs.keys())
        print("Start predicting; got log keys: {}".format(keys))

    def on_predict_end(self, logs=None):
        keys = list(logs.keys())
        print("Stop predicting; got log keys: {}".format(keys))

    def on_train_batch_begin(self, batch, logs=None):
        keys = list(logs.keys())
        print("...Training: start of batch {}; got log keys: {}".format(batch, keys))

    def on_train_batch_end(self, batch, logs=None):
        keys = list(logs.keys())
        print("...Training: end of batch {}; got log keys: {}".format(batch, keys))

    def on_test_batch_begin(self, batch, logs=None):
        keys = list(logs.keys())
        print("...Evaluating: start of batch {}; got log keys: {}".format(batch, keys))

    def on_test_batch_end(self, batch, logs=None):
        keys = list(logs.keys())
        print("...Evaluating: end of batch {}; got log keys: {}".format(batch, keys))

    def on_predict_batch_begin(self, batch, logs=None):
        keys = list(logs.keys())
        print("...Predicting: start of batch {}; got log keys: {}".format(batch, keys))

    def on_predict_batch_end(self, batch, logs=None):
        keys = list(logs.keys())
        print("...Predicting: end of batch {}; got log keys: {}".format(batch, keys))

 

Proviamolo:

 model = get_model()
model.fit(
    x_train,
    y_train,
    batch_size=128,
    epochs=1,
    verbose=0,
    validation_split=0.5,
    callbacks=[CustomCallback()],
)

res = model.evaluate(
    x_test, y_test, batch_size=128, verbose=0, callbacks=[CustomCallback()]
)

res = model.predict(x_test, batch_size=128, callbacks=[CustomCallback()])
 
Starting training; got log keys: []
Start epoch 0 of training; got log keys: []
...Training: start of batch 0; got log keys: []
...Training: end of batch 0; got log keys: ['loss', 'mean_absolute_error']
...Training: start of batch 1; got log keys: []
...Training: end of batch 1; got log keys: ['loss', 'mean_absolute_error']
...Training: start of batch 2; got log keys: []
...Training: end of batch 2; got log keys: ['loss', 'mean_absolute_error']
...Training: start of batch 3; got log keys: []
...Training: end of batch 3; got log keys: ['loss', 'mean_absolute_error']
Start testing; got log keys: []
...Evaluating: start of batch 0; got log keys: []
...Evaluating: end of batch 0; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 1; got log keys: []
...Evaluating: end of batch 1; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 2; got log keys: []
...Evaluating: end of batch 2; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 3; got log keys: []
...Evaluating: end of batch 3; got log keys: ['loss', 'mean_absolute_error']
Stop testing; got log keys: []
End epoch 0 of training; got log keys: ['loss', 'mean_absolute_error', 'val_loss', 'val_mean_absolute_error']
Stop training; got log keys: []
Start testing; got log keys: []
...Evaluating: start of batch 0; got log keys: []
...Evaluating: end of batch 0; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 1; got log keys: []
...Evaluating: end of batch 1; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 2; got log keys: []
...Evaluating: end of batch 2; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 3; got log keys: []
...Evaluating: end of batch 3; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 4; got log keys: []
...Evaluating: end of batch 4; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 5; got log keys: []
...Evaluating: end of batch 5; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 6; got log keys: []
...Evaluating: end of batch 6; got log keys: ['loss', 'mean_absolute_error']
...Evaluating: start of batch 7; got log keys: []
...Evaluating: end of batch 7; got log keys: ['loss', 'mean_absolute_error']
Stop testing; got log keys: []
Start predicting; got log keys: []
...Predicting: start of batch 0; got log keys: []
...Predicting: end of batch 0; got log keys: ['outputs']
...Predicting: start of batch 1; got log keys: []
...Predicting: end of batch 1; got log keys: ['outputs']
...Predicting: start of batch 2; got log keys: []
...Predicting: end of batch 2; got log keys: ['outputs']
...Predicting: start of batch 3; got log keys: []
...Predicting: end of batch 3; got log keys: ['outputs']
...Predicting: start of batch 4; got log keys: []
...Predicting: end of batch 4; got log keys: ['outputs']
...Predicting: start of batch 5; got log keys: []
...Predicting: end of batch 5; got log keys: ['outputs']
...Predicting: start of batch 6; got log keys: []
...Predicting: end of batch 6; got log keys: ['outputs']
...Predicting: start of batch 7; got log keys: []
...Predicting: end of batch 7; got log keys: ['outputs']
Stop predicting; got log keys: []

Utilizzo dei logs dict

Il dict dei logs contiene il valore di perdita e tutte le metriche alla fine di un batch o di un'epoca. L'esempio include la perdita e l'errore assoluto medio.

 class LossAndErrorPrintingCallback(keras.callbacks.Callback):
    def on_train_batch_end(self, batch, logs=None):
        print("For batch {}, loss is {:7.2f}.".format(batch, logs["loss"]))

    def on_test_batch_end(self, batch, logs=None):
        print("For batch {}, loss is {:7.2f}.".format(batch, logs["loss"]))

    def on_epoch_end(self, epoch, logs=None):
        print(
            "The average loss for epoch {} is {:7.2f} "
            "and mean absolute error is {:7.2f}.".format(
                epoch, logs["loss"], logs["mean_absolute_error"]
            )
        )


model = get_model()
model.fit(
    x_train,
    y_train,
    batch_size=128,
    epochs=2,
    verbose=0,
    callbacks=[LossAndErrorPrintingCallback()],
)

res = model.evaluate(
    x_test,
    y_test,
    batch_size=128,
    verbose=0,
    callbacks=[LossAndErrorPrintingCallback()],
)
 
For batch 0, loss is   30.07.
For batch 1, loss is  413.20.
For batch 2, loss is  284.62.
For batch 3, loss is  215.74.
For batch 4, loss is  174.43.
For batch 5, loss is  146.54.
For batch 6, loss is  126.53.
For batch 7, loss is  114.00.
The average loss for epoch 0 is  114.00 and mean absolute error is    5.88.
For batch 0, loss is    5.26.
For batch 1, loss is    5.16.
For batch 2, loss is    4.90.
For batch 3, loss is    4.91.
For batch 4, loss is    4.82.
For batch 5, loss is    4.64.
For batch 6, loss is    4.51.
For batch 7, loss is    4.52.
The average loss for epoch 1 is    4.52 and mean absolute error is    1.71.
For batch 0, loss is    7.47.
For batch 1, loss is    7.51.
For batch 2, loss is    7.33.
For batch 3, loss is    7.34.
For batch 4, loss is    7.35.
For batch 5, loss is    7.48.
For batch 6, loss is    7.44.
For batch 7, loss is    7.36.

Utilizzo dell'attributo self.model

Oltre a ricevere le informazioni del registro quando viene chiamato uno dei loro metodi, i callback hanno accesso al modello associato all'attuale ciclo di formazione / valutazione / inferenza: self.model .

Ecco alcune delle cose che puoi fare con self.model in un callback:

  • Impostare self.model.stop_training = True per interrompere immediatamente l'allenamento.
  • Mutare gli iperparametri dell'ottimizzatore (disponibile come self.model.optimizer ), come self.model.optimizer.learning_rate .
  • Salvare il modello a intervalli periodici.
  • Registrare l'output di model.predict() su alcuni campioni di test alla fine di ogni epoca, da utilizzare come controllo di integrità durante l'allenamento.
  • Estrai visualizzazioni di funzioni intermedie alla fine di ogni epoca, per monitorare ciò che il modello sta imparando nel tempo.
  • eccetera.

Vediamo questo in azione in un paio di esempi.

Esempi di applicazioni di callback di Keras

Arresto anticipato alla perdita minima

Questo primo esempio mostra la creazione di un Callback che interrompe l'allenamento quando viene raggiunto il minimo della perdita, impostando l'attributo self.model.stop_training (booleano). Opzionalmente, puoi fornire un argomento di patience per specificare quante epoche dovremmo aspettare prima di fermarci dopo aver raggiunto un minimo locale.

tf.keras.callbacks.EarlyStopping fornisce tf.keras.callbacks.EarlyStopping più completa e generale.

 import numpy as np


class EarlyStoppingAtMinLoss(keras.callbacks.Callback):
    """Stop training when the loss is at its min, i.e. the loss stops decreasing.

  Arguments:
      patience: Number of epochs to wait after min has been hit. After this
      number of no improvement, training stops.
  """

    def __init__(self, patience=0):
        super(EarlyStoppingAtMinLoss, self).__init__()
        self.patience = patience
        # best_weights to store the weights at which the minimum loss occurs.
        self.best_weights = None

    def on_train_begin(self, logs=None):
        # The number of epoch it has waited when loss is no longer minimum.
        self.wait = 0
        # The epoch the training stops at.
        self.stopped_epoch = 0
        # Initialize the best as infinity.
        self.best = np.Inf

    def on_epoch_end(self, epoch, logs=None):
        current = logs.get("loss")
        if np.less(current, self.best):
            self.best = current
            self.wait = 0
            # Record the best weights if current results is better (less).
            self.best_weights = self.model.get_weights()
        else:
            self.wait += 1
            if self.wait >= self.patience:
                self.stopped_epoch = epoch
                self.model.stop_training = True
                print("Restoring model weights from the end of the best epoch.")
                self.model.set_weights(self.best_weights)

    def on_train_end(self, logs=None):
        if self.stopped_epoch > 0:
            print("Epoch %05d: early stopping" % (self.stopped_epoch + 1))


model = get_model()
model.fit(
    x_train,
    y_train,
    batch_size=64,
    steps_per_epoch=5,
    epochs=30,
    verbose=0,
    callbacks=[LossAndErrorPrintingCallback(), EarlyStoppingAtMinLoss()],
)
 
For batch 0, loss is   27.80.
For batch 1, loss is  392.24.
For batch 2, loss is  269.56.
For batch 3, loss is  205.69.
For batch 4, loss is  166.82.
The average loss for epoch 0 is  166.82 and mean absolute error is    7.96.
For batch 0, loss is    7.27.
For batch 1, loss is    6.18.
For batch 2, loss is    6.08.
For batch 3, loss is    5.83.
For batch 4, loss is    5.61.
The average loss for epoch 1 is    5.61 and mean absolute error is    1.91.
For batch 0, loss is    5.03.
For batch 1, loss is    6.90.
For batch 2, loss is    7.60.
For batch 3, loss is    7.69.
For batch 4, loss is    8.49.
The average loss for epoch 2 is    8.49 and mean absolute error is    2.41.
Restoring model weights from the end of the best epoch.
Epoch 00003: early stopping

<tensorflow.python.keras.callbacks.History at 0x7fa32a9822e8>

Pianificazione dei tassi di apprendimento

In questo esempio, mostriamo come un callback personalizzato può essere utilizzato per modificare dinamicamente il tasso di apprendimento dell'ottimizzatore durante il corso di formazione.

Vedi callbacks.LearningRateScheduler per implementazioni più generali.

 class CustomLearningRateScheduler(keras.callbacks.Callback):
    """Learning rate scheduler which sets the learning rate according to schedule.

  Arguments:
      schedule: a function that takes an epoch index
          (integer, indexed from 0) and current learning rate
          as inputs and returns a new learning rate as output (float).
  """

    def __init__(self, schedule):
        super(CustomLearningRateScheduler, self).__init__()
        self.schedule = schedule

    def on_epoch_begin(self, epoch, logs=None):
        if not hasattr(self.model.optimizer, "lr"):
            raise ValueError('Optimizer must have a "lr" attribute.')
        # Get the current learning rate from model's optimizer.
        lr = float(tf.keras.backend.get_value(self.model.optimizer.learning_rate))
        # Call schedule function to get the scheduled learning rate.
        scheduled_lr = self.schedule(epoch, lr)
        # Set the value back to the optimizer before this epoch starts
        tf.keras.backend.set_value(self.model.optimizer.lr, scheduled_lr)
        print("\nEpoch %05d: Learning rate is %6.4f." % (epoch, scheduled_lr))


LR_SCHEDULE = [
    # (epoch to start, learning rate) tuples
    (3, 0.05),
    (6, 0.01),
    (9, 0.005),
    (12, 0.001),
]


def lr_schedule(epoch, lr):
    """Helper function to retrieve the scheduled learning rate based on epoch."""
    if epoch < LR_SCHEDULE[0][0] or epoch > LR_SCHEDULE[-1][0]:
        return lr
    for i in range(len(LR_SCHEDULE)):
        if epoch == LR_SCHEDULE[i][0]:
            return LR_SCHEDULE[i][1]
    return lr


model = get_model()
model.fit(
    x_train,
    y_train,
    batch_size=64,
    steps_per_epoch=5,
    epochs=15,
    verbose=0,
    callbacks=[
        LossAndErrorPrintingCallback(),
        CustomLearningRateScheduler(lr_schedule),
    ],
)
 

Epoch 00000: Learning rate is 0.1000.
For batch 0, loss is   36.98.
For batch 1, loss is  505.58.
For batch 2, loss is  344.37.
For batch 3, loss is  260.42.
For batch 4, loss is  210.08.
The average loss for epoch 0 is  210.08 and mean absolute error is    8.70.

Epoch 00001: Learning rate is 0.1000.
For batch 0, loss is    6.16.
For batch 1, loss is    5.91.
For batch 2, loss is    5.25.
For batch 3, loss is    5.30.
For batch 4, loss is    5.15.
The average loss for epoch 1 is    5.15 and mean absolute error is    1.84.

Epoch 00002: Learning rate is 0.1000.
For batch 0, loss is    8.28.
For batch 1, loss is    7.63.
For batch 2, loss is    6.94.
For batch 3, loss is    6.69.
For batch 4, loss is    6.24.
The average loss for epoch 2 is    6.24 and mean absolute error is    1.98.

Epoch 00003: Learning rate is 0.0500.
For batch 0, loss is    6.48.
For batch 1, loss is    5.40.
For batch 2, loss is    4.70.
For batch 3, loss is    4.45.
For batch 4, loss is    4.08.
The average loss for epoch 3 is    4.08 and mean absolute error is    1.64.

Epoch 00004: Learning rate is 0.0500.
For batch 0, loss is    3.30.
For batch 1, loss is    4.07.
For batch 2, loss is    4.14.
For batch 3, loss is    4.02.
For batch 4, loss is    4.07.
The average loss for epoch 4 is    4.07 and mean absolute error is    1.62.

Epoch 00005: Learning rate is 0.0500.
For batch 0, loss is    4.81.
For batch 1, loss is    5.43.
For batch 2, loss is    4.83.
For batch 3, loss is    4.90.
For batch 4, loss is    4.58.
The average loss for epoch 5 is    4.58 and mean absolute error is    1.73.

Epoch 00006: Learning rate is 0.0100.
For batch 0, loss is    2.87.
For batch 1, loss is    3.13.
For batch 2, loss is    2.93.
For batch 3, loss is    3.02.
For batch 4, loss is    3.08.
The average loss for epoch 6 is    3.08 and mean absolute error is    1.41.

Epoch 00007: Learning rate is 0.0100.
For batch 0, loss is    3.33.
For batch 1, loss is    4.50.
For batch 2, loss is    4.32.
For batch 3, loss is    4.17.
For batch 4, loss is    3.97.
The average loss for epoch 7 is    3.97 and mean absolute error is    1.57.

Epoch 00008: Learning rate is 0.0100.
For batch 0, loss is    3.20.
For batch 1, loss is    3.54.
For batch 2, loss is    3.16.
For batch 3, loss is    3.29.
For batch 4, loss is    3.54.
The average loss for epoch 8 is    3.54 and mean absolute error is    1.47.

Epoch 00009: Learning rate is 0.0050.
For batch 0, loss is    3.39.
For batch 1, loss is    3.00.
For batch 2, loss is    3.12.
For batch 3, loss is    3.36.
For batch 4, loss is    3.20.
The average loss for epoch 9 is    3.20 and mean absolute error is    1.43.

Epoch 00010: Learning rate is 0.0050.
For batch 0, loss is    3.72.
For batch 1, loss is    3.55.
For batch 2, loss is    3.21.
For batch 3, loss is    2.98.
For batch 4, loss is    3.02.
The average loss for epoch 10 is    3.02 and mean absolute error is    1.36.

Epoch 00011: Learning rate is 0.0050.
For batch 0, loss is    2.88.
For batch 1, loss is    2.88.
For batch 2, loss is    2.89.
For batch 3, loss is    2.95.
For batch 4, loss is    3.50.
The average loss for epoch 11 is    3.50 and mean absolute error is    1.44.

Epoch 00012: Learning rate is 0.0010.
For batch 0, loss is    3.26.
For batch 1, loss is    3.15.
For batch 2, loss is    3.59.
For batch 3, loss is    3.46.
For batch 4, loss is    3.44.
The average loss for epoch 12 is    3.44 and mean absolute error is    1.44.

Epoch 00013: Learning rate is 0.0010.
For batch 0, loss is    3.09.
For batch 1, loss is    3.34.
For batch 2, loss is    3.34.
For batch 3, loss is    3.31.
For batch 4, loss is    3.13.
The average loss for epoch 13 is    3.13 and mean absolute error is    1.43.

Epoch 00014: Learning rate is 0.0010.
For batch 0, loss is    3.69.
For batch 1, loss is    3.23.
For batch 2, loss is    3.09.
For batch 3, loss is    3.39.
For batch 4, loss is    3.19.
The average loss for epoch 14 is    3.19 and mean absolute error is    1.37.

<tensorflow.python.keras.callbacks.History at 0x7fa31c4a5c18>

Richiamate Keras integrate

Assicurati di controllare i callback di Keras esistenti leggendo i documenti API . Le applicazioni includono la registrazione in CSV, il salvataggio del modello, la visualizzazione delle metriche in TensorBoard e molto altro!