Menulis panggilan balik Anda sendiri

Lihat di TensorFlow.org

Jalankan di Google Colab

Lihat sumber di GitHub

Unduh buku catatan

pengantar

Panggilan balik adalah alat yang ampuh untuk menyesuaikan perilaku model Keras selama pelatihan, evaluasi, atau inferensi. Contohnya termasuk tf.keras.callbacks.TensorBoard untuk memvisualisasikan kemajuan pelatihan dan hasil dengan TensorBoard, atau tf.keras.callbacks.ModelCheckpoint untuk secara berkala menyimpan model Anda selama pelatihan.

Dalam panduan ini, Anda akan belajar apa itu panggilan balik Keras, apa yang bisa dilakukannya, dan bagaimana Anda bisa membangunnya sendiri. Kami menyediakan beberapa demo aplikasi panggilan balik sederhana untuk membantu Anda memulai.

Mempersiapkan

 import tensorflow as tf
from tensorflow import keras
 

Ikhtisar panggilan balik yang keras

Semua panggilan balik keras.callbacks.Callback kelas keras.callbacks.Callback , dan menimpa serangkaian metode yang dipanggil pada berbagai tahap pelatihan, pengujian, dan prediksi. Panggilan balik berguna untuk mendapatkan pandangan tentang status internal dan statistik model selama pelatihan.

Anda dapat meneruskan daftar panggilan balik (sebagai callbacks argumen kata kunci) ke metode model berikut:

• keras.Model.fit()
• keras.Model.evaluate()
• keras.Model.predict()

Ikhtisar metode panggilan balik

Metode global

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

Disebut pada awal fit / evaluate / predict .

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

Disebut pada akhir fit / evaluate / predict .

Metode tingkat batch untuk pelatihan / pengujian / prediksi

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

Disebut tepat sebelum memproses batch selama pelatihan / pengujian / prediksi.

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

Disebut pada akhir pelatihan / pengujian / prediksi batch. Dalam metode ini, logs adalah dict yang berisi hasil metrik.

Metode tingkat zaman (hanya pelatihan)

on_epoch_begin(self, epoch, logs=None)

Disebut pada awal zaman selama pelatihan.

on_epoch_end(self, epoch, logs=None)

Disebut pada akhir zaman selama pelatihan.

Contoh dasar

Mari kita lihat contoh konkret. Untuk memulai, mari impor tensorflow dan tentukan model Sequential Keras yang sederhana:

 # 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

 

Kemudian, muat data MNIST untuk pelatihan dan pengujian dari API dataset 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

Sekarang, tentukan callback kustom sederhana yang mencatat:

• Ketika fit / evaluate / predict mulai & berakhir
• Ketika setiap zaman dimulai & berakhir
• Ketika setiap batch pelatihan dimulai & berakhir
• Ketika setiap evaluasi (tes) batch dimulai & diakhiri
• Ketika setiap inferensi (prediksi) batch dimulai & diakhiri

 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))

 

Mari kita coba:

 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: []

Penggunaan dict logs

logs berisi nilai kerugian, dan semua metrik pada akhir batch atau zaman. Contoh termasuk kerugian dan kesalahan absolut rata-rata.

 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.

Penggunaan atribut self.model

Selain menerima informasi log ketika salah satu metode mereka dipanggil, panggilan balik memiliki akses ke model yang terkait dengan putaran pelatihan / evaluasi / inferensi saat ini: self.model .

Berikut adalah beberapa hal yang dapat Anda lakukan dengan self.model dalam panggilan balik:

• Set self.model.stop_training = True untuk segera mengganggu pelatihan.
• Matikan hyperparameters dari optimizer (tersedia sebagai self.model.optimizer ), seperti self.model.optimizer.learning_rate .
• Simpan model pada interval periode.
• Catat output dari model.predict() pada beberapa sampel uji pada akhir setiap zaman, untuk digunakan sebagai pemeriksaan kewarasan selama pelatihan.
• Ekstrak visualisasi fitur antara pada akhir setiap zaman, untuk memantau apa yang dipelajari model dari waktu ke waktu.
• dll.

Mari kita lihat ini dalam beberapa contoh.

Contoh aplikasi panggilan balik Keras

Berhenti lebih awal dari kerugian minimum

Contoh pertama ini menunjukkan pembuatan Callback yang menghentikan pelatihan ketika jumlah minimum kerugian telah tercapai, dengan mengatur atribut self.model.stop_training (boolean). Secara opsional, Anda dapat memberikan patience argumen untuk menentukan berapa banyak zaman yang harus kita tunggu sebelum berhenti setelah mencapai minimum lokal.

tf.keras.callbacks.EarlyStopping menyediakan tf.keras.callbacks.EarlyStopping yang lebih lengkap dan umum.

 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>

Penjadwalan tingkat pembelajaran

Dalam contoh ini, kami menunjukkan bagaimana Callback khusus dapat digunakan untuk secara dinamis mengubah tingkat pembelajaran pengoptimal selama pelatihan.

Lihat callbacks.LearningRateScheduler untuk implementasi yang lebih umum.

 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>

Panggilan balik Keras bawaan

Pastikan untuk memeriksa panggilan balik Keras yang ada dengan membaca dokumentasi API . Aplikasi termasuk masuk ke CSV, menyimpan model, memvisualisasikan metrik di TensorBoard, dan banyak lagi!