TensorFlow 2.3.0
更新时间：2023-01-18
TensorFlow
基于tensorflow框架的MNIST图像分类任务示例代码，训练数据集点击这里下载
单机训练（计算节点数为1），示例代码如下：
"""
tf train demo
"""
import tensorflow as tf
import os
mnist = tf.keras.datasets.mnist
work_path = os.getcwd()
(x_train, y_train), (x_test, y_test) = mnist.load_data('%s/train_data/mnist.npz' % work_path)
x_train, x_test = x_train / 255.0, x_test / 255.0
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test, verbose=2)
model.save('./output/')分布式训练（计算节点数大于1），示例代码如下：
说明：demo分布式程序没有做数据的分片操作，仅供参考
"""
tf horovod train demo
"""
import tensorflow as tf
import horovod.tensorflow as hvd
import os
# Horovod: initialize Horovod.
hvd.init()
# Horovod: pin GPU to be used to process local rank (one GPU per process)
gpus = tf.config.experimental.list_physical_devices('GPU')
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
if gpus:
tf.config.experimental.set_visible_devices(gpus[hvd.local_rank()], 'GPU')
work_path = os.getcwd()
(mnist_images, mnist_labels), _ = \
tf.keras.datasets.mnist.load_data('%s/train_data/mnist.npz' % work_path)
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')
])
loss = tf.losses.SparseCategoricalCrossentropy()
# Horovod: adjust learning rate based on number of GPUs.
opt = tf.optimizers.Adam(0.001 * hvd.size())
@tf.function
def training_step(images, labels, first_batch):
"""
:param images:
:param labels:
:param first_batch:
:return:
"""
with tf.GradientTape() as tape:
probs = mnist_model(images, training=True)
loss_value = loss(labels, probs)
# Horovod: add Horovod Distributed GradientTape.
tape = hvd.DistributedGradientTape(tape)
grads = tape.gradient(loss_value, mnist_model.trainable_variables)
opt.apply_gradients(zip(grads, mnist_model.trainable_variables))
# 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.
#
# Note: broadcast should be done after the first gradient step to ensure optimizer
# initialization.
if first_batch:
hvd.broadcast_variables(mnist_model.variables, root_rank=0)
hvd.broadcast_variables(opt.variables(), root_rank=0)
return loss_value
# Horovod: adjust number of steps based on number of GPUs.
for batch, (images, labels) in enumerate(dataset.take(10000 // hvd.size())):
loss_value = training_step(images, labels, batch == 0)
if batch % 10 == 0 and hvd.local_rank() == 0:
print('Step #%d\tLoss: %.6f' % (batch, loss_value))
# Horovod: save model only on worker 0 to prevent other workers from
# corrupting it.
if hvd.rank() == 0:
mnist_model.save('./output/')