TensorFlow Addons Callbacks: TimeStopping

Overview

This notebook will demonstrate how to use TimeStopping Callback in TensorFlow Addons.

Setup

pip install -U tensorflow-addons

import tensorflow_addons as tfa

from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten

Import and Normalize Data

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# normalize data
x_train, x_test = x_train / 255.0, x_test / 255.0

Build Simple MNIST CNN Model

# build the model using the Sequential API
model = Sequential()
model.add(Flatten(input_shape=(28, 28)))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))

model.compile(optimizer='adam',
              loss = 'sparse_categorical_crossentropy',
              metrics=['accuracy'])

Simple TimeStopping Usage

# initialize TimeStopping callback 
time_stopping_callback = tfa.callbacks.TimeStopping(seconds=5, verbose=1)

# train the model with tqdm_callback
# make sure to set verbose = 0 to disable
# the default progress bar.
model.fit(x_train, y_train,
          batch_size=64,
          epochs=100,
          callbacks=[time_stopping_callback],
          validation_data=(x_test, y_test))

Epoch 1/100
938/938 [==============================] - 3s 2ms/step - loss: 0.3420 - accuracy: 0.9022 - val_loss: 0.1628 - val_accuracy: 0.9522
Epoch 2/100
938/938 [==============================] - 2s 2ms/step - loss: 0.1636 - accuracy: 0.9514 - val_loss: 0.1122 - val_accuracy: 0.9656
Epoch 3/100
938/938 [==============================] - 2s 2ms/step - loss: 0.1213 - accuracy: 0.9642 - val_loss: 0.0932 - val_accuracy: 0.9711
Timed stopping at epoch 3 after training for 0:00:05
<keras.callbacks.History at 0x7fb5df60c130>