Avoir une question? Connectez-vous avec la communauté sur le forum TensorFlow Visiter le forum

Rédaction de vos propres rappels

Voir sur TensorFlow.org Exécuter dans Google Colab Afficher la source sur GitHub Télécharger le cahier

introduction

Un rappel est un outil puissant pour personnaliser le comportement d'un modèle Keras pendant l'entraînement, l'évaluation ou l'inférence. Les exemples incluent tf.keras.callbacks.TensorBoard pour visualiser la progression et les résultats de l'entraînement avec TensorBoard, ou tf.keras.callbacks.ModelCheckpoint pour enregistrer périodiquement votre modèle pendant l'entraînement.

Dans ce guide, vous apprendrez ce qu'est un rappel Keras, ce qu'il peut faire et comment vous pouvez créer le vôtre. Nous fournissons quelques démos d'applications de rappel simples pour vous aider à démarrer.

Installer

import tensorflow as tf
from tensorflow import keras

Présentation des rappels Keras

Tous les callbacks sous- keras.callbacks.Callback classe keras.callbacks.Callback et remplacent un ensemble de méthodes appelées à différentes étapes d'entraînement, de test et de prédiction. Les rappels sont utiles pour obtenir une vue sur les états internes et les statistiques du modèle pendant l'entraînement.

Vous pouvez transmettre une liste de rappels (en tant que callbacks argument de mot-clé) aux méthodes de modèle suivantes:

Un aperçu des méthodes de rappel

Méthodes globales

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

Appelé au début de l' fit / evaluate / predict .

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

Appelé à la fin de l' fit / evaluate / predict .

Méthodes au niveau du lot pour la formation / le test / la prévision

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

Appelé juste avant de traiter un lot pendant la formation / les tests / les prévisions.

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

Appelé à la fin de la formation / du test / de la prédiction d'un lot. Dans cette méthode, logs est un dict contenant les résultats des métriques.

Méthodes au niveau de l'époque (formation uniquement)

on_epoch_begin(self, epoch, logs=None)

Appelé au début d'une époque pendant l'entraînement.

on_epoch_end(self, epoch, logs=None)

Appelé à la fin d'une époque pendant l'entraînement.

Un exemple basique

Jetons un coup d'œil à un exemple concret. Pour commencer, importons tensorflow et définissons un modèle Keras séquentiel simple:

# 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

Ensuite, chargez les données MNIST pour l'entraînement et les tests à partir de l'API des ensembles de données 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

Maintenant, définissez un simple rappel personnalisé qui enregistre:

  • Quand fit / evaluate / predict début et la fin
  • Quand chaque époque commence et se termine
  • Quand chaque lot de formation commence et se termine
  • Quand chaque lot d'évaluation (test) commence et se termine
  • Quand chaque lot d'inférence (prédiction) commence et se termine
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))

Essayons-le:

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: ['loss', 'mean_absolute_error']
End epoch 0 of training; got log keys: ['loss', 'mean_absolute_error', 'val_loss', 'val_mean_absolute_error']
Stop training; got log keys: ['loss', 'mean_absolute_error', 'val_loss', 'val_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']
...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: ['loss', 'mean_absolute_error']
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: []

Utilisation des logs dict

Le logs dict contient la valeur de la perte et toutes les métriques à la fin d'un lot ou d'une époque. L'exemple comprend la perte et l'erreur absolue moyenne.

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   27.09.
For batch 1, loss is  455.54.
For batch 2, loss is  310.84.
For batch 3, loss is  235.38.
For batch 4, loss is  189.59.
For batch 5, loss is  159.45.
For batch 6, loss is  137.62.
For batch 7, loss is  123.95.
The average loss for epoch 0 is  123.95 and mean absolute error is    6.04.
For batch 0, loss is    4.68.
For batch 1, loss is    4.44.
For batch 2, loss is    4.25.
For batch 3, loss is    4.19.
For batch 4, loss is    4.10.
For batch 5, loss is    4.15.
For batch 6, loss is    4.41.
For batch 7, loss is    4.44.
The average loss for epoch 1 is    4.44 and mean absolute error is    1.70.
For batch 0, loss is    4.60.
For batch 1, loss is    4.22.
For batch 2, loss is    4.30.
For batch 3, loss is    4.23.
For batch 4, loss is    4.37.
For batch 5, loss is    4.35.
For batch 6, loss is    4.34.
For batch 7, loss is    4.28.

Utilisation de l'attribut self.model

En plus de recevoir des informations de journal lorsque l'une de leurs méthodes est appelée, les callbacks ont accès au modèle associé à la ronde actuelle de formation / évaluation / inférence: self.model .

Voici quelques-unes des choses que vous pouvez faire avec self.model dans un rappel:

  • Définissez self.model.stop_training = True pour interrompre immédiatement l'entraînement.
  • Mutation des hyperparamètres de l'optimiseur (disponibles sous le nom de self.model.optimizer ), tels que self.model.optimizer.learning_rate .
  • Enregistrez le modèle à intervalles réguliers.
  • Enregistrez la sortie de model.predict() sur quelques échantillons de test à la fin de chaque époque, à utiliser comme contrôle de cohérence pendant la formation.
  • Extrayez des visualisations des caractéristiques intermédiaires à la fin de chaque époque, pour surveiller ce que le modèle apprend au fil du temps.
  • etc.

Voyons cela en action dans quelques exemples.

Exemples d'applications de rappel Keras

Arrêt précoce avec une perte minimale

Ce premier exemple montre la création d'un Callback qui arrête l'entraînement lorsque le minimum de perte a été atteint, en définissant l'attribut self.model.stop_training (booléen). En option, vous pouvez fournir un argument patience pour spécifier le nombre d'époques à attendre avant de s'arrêter après avoir atteint un minimum local.

tf.keras.callbacks.EarlyStopping fournit une implémentation plus complète et générale.

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   36.12.
For batch 1, loss is  473.15.
For batch 2, loss is  324.54.
For batch 3, loss is  245.95.
For batch 4, loss is  198.35.
The average loss for epoch 0 is  198.35 and mean absolute error is    8.54.
For batch 0, loss is    8.53.
For batch 1, loss is    7.74.
For batch 2, loss is    6.75.
For batch 3, loss is    7.01.
For batch 4, loss is    7.12.
The average loss for epoch 1 is    7.12 and mean absolute error is    2.20.
For batch 0, loss is    6.39.
For batch 1, loss is    6.75.
For batch 2, loss is    6.46.
For batch 3, loss is    6.55.
For batch 4, loss is    7.21.
The average loss for epoch 2 is    7.21 and mean absolute error is    2.20.
Restoring model weights from the end of the best epoch.
Epoch 00003: early stopping
<tensorflow.python.keras.callbacks.History at 0x7f39a680ffd0>

Planification du taux d'apprentissage

Dans cet exemple, nous montrons comment un rappel personnalisé peut être utilisé pour modifier dynamiquement le taux d'apprentissage de l'optimiseur au cours de la formation.

Voir callbacks.LearningRateScheduler pour une implémentation plus générale.

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   28.49.
For batch 1, loss is  432.45.
For batch 2, loss is  298.60.
For batch 3, loss is  227.34.
For batch 4, loss is  183.34.
The average loss for epoch 0 is  183.34 and mean absolute error is    8.37.

Epoch 00001: Learning rate is 0.1000.
For batch 0, loss is    5.96.
For batch 1, loss is    6.24.
For batch 2, loss is    5.68.
For batch 3, loss is    5.64.
For batch 4, loss is    5.41.
The average loss for epoch 1 is    5.41 and mean absolute error is    1.89.

Epoch 00002: Learning rate is 0.1000.
For batch 0, loss is    4.84.
For batch 1, loss is    4.66.
For batch 2, loss is    5.96.
For batch 3, loss is    7.54.
For batch 4, loss is    8.48.
The average loss for epoch 2 is    8.48 and mean absolute error is    2.29.

Epoch 00003: Learning rate is 0.0500.
For batch 0, loss is   11.10.
For batch 1, loss is    6.77.
For batch 2, loss is    5.99.
For batch 3, loss is    5.07.
For batch 4, loss is    5.03.
The average loss for epoch 3 is    5.03 and mean absolute error is    1.76.

Epoch 00004: Learning rate is 0.0500.
For batch 0, loss is    4.72.
For batch 1, loss is    4.30.
For batch 2, loss is    4.20.
For batch 3, loss is    4.29.
For batch 4, loss is    4.30.
The average loss for epoch 4 is    4.30 and mean absolute error is    1.66.

Epoch 00005: Learning rate is 0.0500.
For batch 0, loss is    5.52.
For batch 1, loss is    5.15.
For batch 2, loss is    4.51.
For batch 3, loss is    4.40.
For batch 4, loss is    4.80.
The average loss for epoch 5 is    4.80 and mean absolute error is    1.77.

Epoch 00006: Learning rate is 0.0100.
For batch 0, loss is    7.07.
For batch 1, loss is    6.72.
For batch 2, loss is    5.62.
For batch 3, loss is    4.79.
For batch 4, loss is    4.68.
The average loss for epoch 6 is    4.68 and mean absolute error is    1.69.

Epoch 00007: Learning rate is 0.0100.
For batch 0, loss is    2.61.
For batch 1, loss is    2.50.
For batch 2, loss is    2.76.
For batch 3, loss is    2.96.
For batch 4, loss is    3.14.
The average loss for epoch 7 is    3.14 and mean absolute error is    1.38.

Epoch 00008: Learning rate is 0.0100.
For batch 0, loss is    4.12.
For batch 1, loss is    3.91.
For batch 2, loss is    3.37.
For batch 3, loss is    3.30.
For batch 4, loss is    3.08.
The average loss for epoch 8 is    3.08 and mean absolute error is    1.37.

Epoch 00009: Learning rate is 0.0050.
For batch 0, loss is    5.81.
For batch 1, loss is    5.12.
For batch 2, loss is    4.53.
For batch 3, loss is    4.08.
For batch 4, loss is    3.95.
The average loss for epoch 9 is    3.95 and mean absolute error is    1.56.

Epoch 00010: Learning rate is 0.0050.
For batch 0, loss is    2.73.
For batch 1, loss is    2.83.
For batch 2, loss is    2.75.
For batch 3, loss is    3.07.
For batch 4, loss is    2.93.
The average loss for epoch 10 is    2.93 and mean absolute error is    1.35.

Epoch 00011: Learning rate is 0.0050.
For batch 0, loss is    3.33.
For batch 1, loss is    3.60.
For batch 2, loss is    3.77.
For batch 3, loss is    3.51.
For batch 4, loss is    3.43.
The average loss for epoch 11 is    3.43 and mean absolute error is    1.40.

Epoch 00012: Learning rate is 0.0010.
For batch 0, loss is    4.29.
For batch 1, loss is    3.72.
For batch 2, loss is    3.78.
For batch 3, loss is    3.61.
For batch 4, loss is    3.47.
The average loss for epoch 12 is    3.47 and mean absolute error is    1.46.

Epoch 00013: Learning rate is 0.0010.
For batch 0, loss is    3.01.
For batch 1, loss is    3.10.
For batch 2, loss is    3.20.
For batch 3, loss is    3.00.
For batch 4, loss is    3.16.
The average loss for epoch 13 is    3.16 and mean absolute error is    1.36.

Epoch 00014: Learning rate is 0.0010.
For batch 0, loss is    5.22.
For batch 1, loss is    3.80.
For batch 2, loss is    3.61.
For batch 3, loss is    3.45.
For batch 4, loss is    3.43.
The average loss for epoch 14 is    3.43 and mean absolute error is    1.43.
<tensorflow.python.keras.callbacks.History at 0x7f39a6875400>

Rappels Keras intégrés

Assurez-vous de vérifier les rappels Keras existants en lisant la documentation de l' API . Les applications incluent la journalisation au format CSV, l'enregistrement du modèle, la visualisation des métriques dans TensorBoard et bien plus encore!