TensorFlow2.0 - C2 Guide - 2 Keras

1 Keras overview

https://www.tensorflow.org/guide/keras
建立模型步骤compile fit evaluate predict和输入dataset
高级方法functional API, subclassing model, custom layer, callbacks
save and restore, eager execution, distribution

1.1 Import tf.keras

from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf
from tensorflow import keras

not uptodate version compared to keras
defaults to the checkpoint format not HDF5(pass save_format='h5' to use)

1.2 Build a simple model

序列模型

model = tf.keras.Sequential()
# Adds a densely-connected layer with 64 units to the model:
model.add(layers.Dense(64, activation='relu'))
# Add another:
model.add(layers.Dense(64, activation='relu'))
# Add a softmax layer with 10 output units:
model.add(layers.Dense(10, activation='softmax'))

这些层可以配置
activation激活函数, kernel_initializer和bias_initializer初始化方案, kernel_regularizer和bias_regularizer 正则化方案

1.3 训练和评估

model = tf.keras.Sequential([
# Adds a densely-connected layer with 64 units to the model:
layers.Dense(64, activation='relu', input_shape=(32,)),
# Add another:
layers.Dense(64, activation='relu'),
# Add a softmax layer with 10 output units:
layers.Dense(10, activation='softmax')])

model.compile(optimizer=tf.keras.optimizers.Adam(0.01),
              loss='categorical_crossentropy',
              metrics=['accuracy'])

numpy输入

model.compile(optimizer=tf.train.AdamOptimizer(0.001),
              loss='categorical_crossentropy',
              metrics=['accuracy'])

optimizer: 训练方法，loss：优化函数，metrics：训练监控

import numpy as np

data = np.random.random((1000, 32))
labels = np.random.random((1000, 10))

val_data = np.random.random((100, 32))
val_labels = np.random.random((100, 10))

model.fit(data, labels, epochs=10, batch_size=32,
          validation_data=(val_data, val_labels))

epochs：训练周期（整个输入数据的一次迭代），batch_size：批次大小 (每次iterate用多少数据迭代)
validation_data：在每个训练周期结束加上显示验证集的数据和指标

dataset输入

# Instantiates a toy dataset instance:
dataset = tf.data.Dataset.from_tensor_slices((data, labels))
dataset = dataset.batch(32)

model.fit(dataset, epochs=10)

dataset = tf.data.Dataset.from_tensor_slices((data, labels))
dataset = dataset.batch(32)

val_dataset = tf.data.Dataset.from_tensor_slices((val_data, val_labels))
val_dataset = val_dataset.batch(32)

model.fit(dataset, epochs=10,
          validation_data=val_dataset)

评估和预测

# With Numpy arrays
data = np.random.random((1000, 32))
labels = np.random.random((1000, 10))

model.evaluate(data, labels, batch_size=32)

# With a Dataset
dataset = tf.data.Dataset.from_tensor_slices((data, labels))
dataset = dataset.batch(32)

model.evaluate(dataset)

result = model.predict(data, batch_size=32)
print(result.shape)

1.4 构建复杂模型

函数式API
Types of models:
Multi-input
Multi-output
Models with shared layers
Models with non-sequential data flows

inputs = tf.keras.Input(shape=(32,))  # Returns a placeholder tensor

# A layer instance is callable on a tensor, and returns a tensor.
x = layers.Dense(64, activation='relu')(inputs)
x = layers.Dense(64, activation='relu')(x)
predictions = layers.Dense(10, activation='softmax')(x)

# kernel
model = tf.keras.Model(inputs=inputs, outputs=predictions)

# The compile step specifies the training configuration.
model.compile(optimizer=tf.train.RMSPropOptimizer(0.001),
              loss='categorical_crossentropy',
              metrics=['accuracy'])

# Trains for 5 epochs
model.fit(data, labels, batch_size=32, epochs=5)

Model subclassing
可以定制自己的model

class MyModel(tf.keras.Model):

  def __init__(self, num_classes=10):
    super(MyModel, self).__init__(name='my_model')
    self.num_classes = num_classes
    # Define your layers here.
    self.dense_1 = layers.Dense(32, activation='relu')
    self.dense_2 = layers.Dense(num_classes, activation='sigmoid')

  def call(self, inputs):
    # Define your forward pass here,
    # using layers you previously defined (in `__init__`).
    x = self.dense_1(inputs)
    return self.dense_2(x)

Custom layers
可以定制自己的层

class MyLayer(layers.Layer):

  def __init__(self, output_dim, **kwargs):
    self.output_dim = output_dim
    super(MyLayer, self).__init__(**kwargs)

  def build(self, input_shape):
    # Create a trainable weight variable for this layer.
    self.kernel = self.add_weight(name='kernel',
                                  shape=(input_shape[1], self.output_dim),
                                  initializer='uniform',
                                  trainable=True)

  def call(self, inputs):
    return tf.matmul(inputs, self.kernel)

  def get_config(self):
    base_config = super(MyLayer, self).get_config()
    base_config['output_dim'] = self.output_dim
    return base_config

  @classmethod
  def from_config(cls, config):
    return cls(**config)

1.5 Callbacks

四种ModelCheckpoint, LearningRateScheduler, EarlyStopping, TensorBoard
https://www.tensorflow.org/guide/summaries_and_tensorboard

callbacks = [
  # Interrupt training if `val_loss` stops improving for over 2 epochs
  tf.keras.callbacks.EarlyStopping(patience=2, monitor='val_loss'),
  # Write TensorBoard logs to `./logs` directory
  tf.keras.callbacks.TensorBoard(log_dir='./logs')
]
model.fit(data, labels, batch_size=32, epochs=5, callbacks=callbacks,
          validation_data=(val_data, val_labels))

1.6 Save and restore

save just the weights values
save just the model configuration
save the entire model:

# Create a trivial model
model = tf.keras.Sequential([
  layers.Dense(64, activation='relu', input_shape=(32,)),
  layers.Dense(10, activation='softmax')
])
model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])
model.fit(data, labels, batch_size=32, epochs=5)


# Save entire model to a HDF5 file
model.save('my_model.h5')

# Recreate the exact same model, including weights and optimizer.
model = tf.keras.models.load_model('my_model.h5')

1.7 Eager execution

有利于测试model subclassing和custom layers

1.8 Distribution

多GPU

strategy = tf.distribute.MirroredStrategy()

with strategy.scope():
  model = tf.keras.Sequential()
  model.add(layers.Dense(16, activation='relu', input_shape=(10,)))
  model.add(layers.Dense(1, activation='sigmoid'))

  optimizer = tf.keras.optimizers.SGD(0.2)

  model.compile(loss='binary_crossentropy', optimizer=optimizer)

model.summary()

2 Keras functional API

3 Train and evaluate

3.1 Using buid-in training and evaluation loops

Specifying a loss, metrics, and an optimizer
Custom losses/metrics
training and evaluation from numpy
training and evaluation from Datasets
passing data to mulit-input, multi-output models
Callbacks
Visualizing loss and metrics during training