Keras guide

1,Sequential model

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'))

2,Layers

# Create a sigmoid layer:

layers.Dense(64, activation='sigmoid')

# Or:

layers.Dense(64, activation=tf.sigmoid)

# A linear layer with L1 regularization of factor 0.01 applied to the kernel matrix:

layers.Dense(64, kernel_regularizer=tf.keras.regularizers.l1(0.01))

# A linear layer with L2 regularization of factor 0.01 applied to the bias vector:

layers.Dense(64, bias_regularizer=tf.keras.regularizers.l2(0.01))

# A linear layer with a kernel initialized to a random orthogonal matrix:

layers.Dense(64, kernel_initializer='orthogonal')

# A linear layer with a bias vector initialized to 2.0s:

layers.Dense(64, bias_initializer=tf.keras.initializers.constant(2.0))

3,Model

# Instantiates a toy dataset instance:

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

dataset = dataset.batch(32)

dataset = dataset.repeat()

# Don't forget to specify `steps_per_epoch` when calling `fit` on a dataset.

model.fit(dataset, epochs=10, steps_per_epoch=30)

4,steps

# Instantiates a toy dataset instance:

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

dataset = dataset.batch(32)

dataset = dataset.repeat()

# Don't forget to specify `steps_per_epoch` when calling `fit` on a dataset.

model.fit(dataset, epochs=10, steps_per_epoch=30)

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

dataset = dataset.batch(32).repeat()

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

val_dataset = val_dataset.batch(32).repeat()

model.fit(dataset, epochs=10, steps_per_epoch=30,

validation_data=val_dataset,

validation_steps=3)

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

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

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

model.evaluate(dataset, steps=30)

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

print(result.shape)

5,Functional API

• Multi-input models,
• Multi-output models,
• Models with shared layers (the same layer called several times),
• Models with non-sequential data flows (e.g. residual connections).

Building a model with the functional API works like this:

1. A layer instance is callable and returns a tensor.
2. Input tensors and output tensors are used to define a tf.keras.Model instance.
3. This model is trained just like the Sequential model.

5.1, inout and output

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)

5.2,Wrapped in model

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)

6,Model subclassing

Build a fully-customizable model by subclassing tf.keras.Model and defining your own forward pass. Create layers in the __init__ method and set them as attributes of the class instance. Define the forward pass in the call method.

Model subclassing is particularly useful when eager execution is enabled since the forward pass can be written imperatively.

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)

def compute_output_shape(self, input_shape):

# You need to override this function if you want to use the subclassed model

# as part of a functional-style model.

# Otherwise, this method is optional.

shape = tf.TensorShape(input_shape).as_list()

shape[-1] = self.num_classes

return tf.TensorShape(shape)

model = MyModel(num_classes=10)

# 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)

7,Custom layers

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):

shape = tf.TensorShape((input_shape[1], self.output_dim))

# Create a trainable weight variable for this layer.

self.kernel = self.add_weight(name='kernel',

shape=shape,

initializer='uniform',

trainable=True)

# Make sure to call the `build` method at the end

super(MyLayer, self).build(input_shape)

def call(self, inputs):

return tf.matmul(inputs, self.kernel)

def compute_output_shape(self, input_shape):

shape = tf.TensorShape(input_shape).as_list()

shape[-1] = self.output_dim

return tf.TensorShape(shape)

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)

model = tf.keras.Sequential([

MyLayer(10),

layers.Activation('softmax')])

# 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)

8,callbacks

• tf.keras.callbacks.ModelCheckpoint: Save checkpoints of your model at regular intervals.
• tf.keras.callbacks.LearningRateScheduler: Dynamically change the learning rate.
• tf.keras.callbacks.EarlyStopping: Interrupt training when validation performance has stopped improving.
• tf.keras.callbacks.TensorBoard: Monitor the model's behavior using 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))

9,Save and restore

9.1,Weights only

# Save weights to a HDF5 file

model.save_weights('my_model.h5', save_format='h5')

# Restore the model's state

model.load_weights('my_model.h5')

9.2,configurations only

# Serialize a model to JSON format

json_string = model.to_json()

json_string

import json

import pprint

pprint.pprint(json.loads(json_string))

fresh_model = tf.keras.models.model_from_json(json_string)

yaml_string = model.to_yaml()

print(yaml_string)

fresh_model = tf.keras.models.model_from_yaml(yaml_string)

9.3,Entire model

# Create a trivial model

model = tf.keras.Sequential([

layers.Dense(10, activation='softmax', 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')

10,Eager execution

Eager execution is an imperative programming environment that evaluates operations immediately. This is not required for Keras, but is supported by tf.keras and useful for inspecting your program and debugging.

All of the tf.keras model-building APIs are compatible with eager execution. And while the Sequential and functional APIs can be used, eager execution especially benefits model subclassing and building custom layers—the APIs that require you to write the forward pass as code (instead of the APIs that create models by assembling existing layers).

11,Estimators

11.1,converto

A tf.keras.Model can be trained with the tf.estimator API by converting the model to an tf.estimator.Estimator object with tf.keras.estimator.model_to_estimator

model = tf.keras.Sequential([layers.Dense(10,activation='softmax'),

layers.Dense(10,activation='softmax')])

model.compile(optimizer=tf.train.RMSPropOptimizer(0.001),

loss='categorical_crossentropy',

metrics=['accuracy'])

estimator = tf.keras.estimator.model_to_estimator(model)

11.2,

model = tf.keras.Sequential()

model.add(layers.Dense(16, activation='relu', input_shape=(10,)))

model.add(layers.Dense(1, activation='sigmoid'))

optimizer = tf.train.GradientDescentOptimizer(0.2)

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

model.summary()

Define an input pipeline

def input_fn():

x = np.random.random((1024, 10))

y = np.random.randint(2, size=(1024, 1))

x = tf.cast(x, tf.float32)

dataset = tf.data.Dataset.from_tensor_slices((x, y))

dataset = dataset.repeat(10)

dataset = dataset.batch(32)

return dataset

Next, create a tf.estimator.RunConfig and set the train_distribute argument to the tf.contrib.distribute.MirroredStrategy instance. When creating MirroredStrategy, you can specify a list of devices or set the num_gpus argument

strategy = tf.contrib.distribute.MirroredStrategy()

config = tf.estimator.RunConfig(train_distribute=strategy)

Convert the Keras model to a tf.estimator.Estimator instance

keras_estimator = tf.keras.estimator.model_to_estimator(

keras_model=model,

config=config,

model_dir='/tmp/model_dir')

keras_estimator.train(input_fn=input_fn, steps=10)