examples/tensorflow2_keras_mnist.py [29:73]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
(mnist_images, mnist_labels), _ = \
    tf.keras.datasets.mnist.load_data(path='mnist-%d.npz' % hvd.rank())

dataset = tf.data.Dataset.from_tensor_slices(
    (tf.cast(mnist_images[..., tf.newaxis] / 255.0, tf.float32),
             tf.cast(mnist_labels, tf.int64))
)
dataset = dataset.repeat().shuffle(10000).batch(128)

mnist_model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(32, [3, 3], activation='relu'),
    tf.keras.layers.Conv2D(64, [3, 3], activation='relu'),
    tf.keras.layers.MaxPooling2D(pool_size=(2, 2)),
    tf.keras.layers.Dropout(0.25),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dropout(0.5),
    tf.keras.layers.Dense(10, activation='softmax')
])

# Horovod: adjust learning rate based on number of GPUs.
scaled_lr = 0.001 * hvd.size()
opt = tf.optimizers.Adam(scaled_lr)

# Horovod: add Horovod DistributedOptimizer.
opt = hvd.DistributedOptimizer(opt)

# Horovod: Specify `experimental_run_tf_function=False` to ensure TensorFlow
# uses hvd.DistributedOptimizer() to compute gradients.
mnist_model.compile(loss=tf.losses.SparseCategoricalCrossentropy(),
                    optimizer=opt,
                    metrics=['accuracy'],
                    experimental_run_tf_function=False)

callbacks = [
    # Horovod: broadcast initial variable states from rank 0 to all other processes.
    # This is necessary to ensure consistent initialization of all workers when
    # training is started with random weights or restored from a checkpoint.
    hvd.callbacks.BroadcastGlobalVariablesCallback(0),

    # Horovod: average metrics among workers at the end of every epoch.
    #
    # Note: This callback must be in the list before the ReduceLROnPlateau,
    # TensorBoard or other metrics-based callbacks.
    hvd.callbacks.MetricAverageCallback(),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



examples/tensorflow2_mnist_ray.py [20:64]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    (mnist_images, mnist_labels), _ = \
        tf.keras.datasets.mnist.load_data(path='mnist-%d.npz' % hvd.rank())

    dataset = tf.data.Dataset.from_tensor_slices(
        (tf.cast(mnist_images[..., tf.newaxis] / 255.0, tf.float32),
         tf.cast(mnist_labels, tf.int64))
    )
    dataset = dataset.repeat().shuffle(10000).batch(128)

    mnist_model = tf.keras.Sequential([
        tf.keras.layers.Conv2D(32, [3, 3], activation='relu'),
        tf.keras.layers.Conv2D(64, [3, 3], activation='relu'),
        tf.keras.layers.MaxPooling2D(pool_size=(2, 2)),
        tf.keras.layers.Dropout(0.25),
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(128, activation='relu'),
        tf.keras.layers.Dropout(0.5),
        tf.keras.layers.Dense(10, activation='softmax')
    ])

    # Horovod: adjust learning rate based on number of GPUs.
    scaled_lr = 0.001 * hvd.size()
    opt = tf.optimizers.Adam(scaled_lr)

    # Horovod: add Horovod DistributedOptimizer.
    opt = hvd.DistributedOptimizer(opt)

    # Horovod: Specify `experimental_run_tf_function=False` to ensure TensorFlow
    # uses hvd.DistributedOptimizer() to compute gradients.
    mnist_model.compile(loss=tf.losses.SparseCategoricalCrossentropy(),
                        optimizer=opt,
                        metrics=['accuracy'],
                        experimental_run_tf_function=False)

    callbacks = [
        # Horovod: broadcast initial variable states from rank 0 to all other processes.
        # This is necessary to ensure consistent initialization of all workers when
        # training is started with random weights or restored from a checkpoint.
        hvd.callbacks.BroadcastGlobalVariablesCallback(0),

        # Horovod: average metrics among workers at the end of every epoch.
        #
        # Note: This callback must be in the list before the ReduceLROnPlateau,
        # TensorBoard or other metrics-based callbacks.
        hvd.callbacks.MetricAverageCallback(),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -