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:
- A layer instance is callable and returns a tensor.
- Input tensors and output tensors are used to define a
tf.keras.Model
instance. - 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_estima
tor
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)
本站文章如无特殊说明,均为本站原创,如若转载,请注明出处:Keras guide - Python技术站