鍵.png)
使用這些基本 REST API 最佳實(shí)踐構(gòu)建出色的 API
你可能也喜歡這些API文章!
tf.keras 可以運(yùn)行任何與 Keras 兼容的代碼，但請注意：
在 Keras 中，您可以通過組合層來構(gòu)建模型。模型（通常）是由層構(gòu)成的圖。最常見的模型類型是層的堆疊：tf.keras.Sequential 模型。
要構(gòu)建一個簡單的全連接網(wǎng)絡(luò)（即多層感知器），請運(yùn)行以下代碼：
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'))我們可以使用很多?tf.keras.layers，它們具有一些相同的構(gòu)造函數(shù)參數(shù)：
以下代碼使用構(gòu)造函數(shù)參數(shù)實(shí)例化?tf.keras.layers. Dense?層：
# 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))構(gòu)建好模型后，通過調(diào)用?compile?方法配置該模型的學(xué)習(xí)流程：
model = tf.keras.Sequential([
# Adds a densely-connected layer with 64 units to the model:
layers.Dense(64, activation='relu'),
# Add another:
layers.Dense(64, activation='relu'),
# Add a softmax layer with 10 output units:
layers.Dense(10, activation='softmax')])
model.compile(optimizer=tf.train.AdamOptimizer(0.001),
loss='categorical_crossentropy',
metrics=['accuracy'])tf.keras.Model.compile 采用三個重要參數(shù)：
以下代碼展示了配置模型以進(jìn)行訓(xùn)練的幾個示例：
# Configure a model for mean-squared error regression.
model.compile(optimizer=tf.train.AdamOptimizer(0.01),
loss='mse', # mean squared error
metrics=['mae']) # mean absolute error
# Configure a model for categorical classification.
model.compile(optimizer=tf.train.RMSPropOptimizer(0.01),
loss=tf.keras.losses.categorical_crossentropy,
metrics=[tf.keras.metrics.categorical_accuracy])對于小型數(shù)據(jù)集，請使用內(nèi)存中的?NumPy?數(shù)組訓(xùn)練和評估模型（https://www.numpy.org/）。使用?fit?方法使模型與訓(xùn)練數(shù)據(jù) “擬合”：
import numpy as np
data = np.random.random((1000, 32))
labels = np.random.random((1000, 10))
model.fit(data, labels, epochs=10, batch_size=32)
Epoch 1/10
1000/1000 [==============================] - 0s 253us/step - loss: 11.5766 - categorical_accuracy: 0.1110
Epoch 2/10
1000/1000 [==============================] - 0s 64us/step - loss: 11.5205 - categorical_accuracy: 0.1070
Epoch 3/10
1000/1000 [==============================] - 0s 70us/step - loss: 11.5146 - categorical_accuracy: 0.1100
Epoch 4/10
1000/1000 [==============================] - 0s 69us/step - loss: 11.5070 - categorical_accuracy: 0.0940
Epoch 5/10
1000/1000 [==============================] - 0s 71us/step - loss: 11.5020 - categorical_accuracy: 0.1150
Epoch 6/10
1000/1000 [==============================] - 0s 72us/step - loss: 11.5019 - categorical_accuracy: 0.1350
Epoch 7/10
1000/1000 [==============================] - 0s 72us/step - loss: 11.5012 - categorical_accuracy: 0.0970
Epoch 8/10
1000/1000 [==============================] - 0s 72us/step - loss: 11.4993 - categorical_accuracy: 0.1180
Epoch 9/10
1000/1000 [==============================] - 0s 69us/step - loss: 11.4905 - categorical_accuracy: 0.1320
Epoch 10/10
1000/1000 [==============================] - 0s 66us/step - loss: 11.4909 - categorical_accuracy: 0.1410tf.keras.Model.fit?采用三個重要參數(shù)：
下面是使用?validation_data?的示例：
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))
Train on 1000 samples, validate on 100 samples
Epoch 1/10
1000/1000 [==============================] - 0s 124us/step - loss: 11.5267 - categorical_accuracy: 0.1070 - val_loss: 11.0015 - val_categorical_accuracy: 0.0500
Epoch 2/10
1000/1000 [==============================] - 0s 72us/step - loss: 11.5243 - categorical_accuracy: 0.0840 - val_loss: 10.9809 - val_categorical_accuracy: 0.1200
Epoch 3/10
1000/1000 [==============================] - 0s 73us/step - loss: 11.5213 - categorical_accuracy: 0.1000 - val_loss: 10.9945 - val_categorical_accuracy: 0.0800
Epoch 4/10
1000/1000 [==============================] - 0s 73us/step - loss: 11.5213 - categorical_accuracy: 0.1080 - val_loss: 10.9967 - val_categorical_accuracy: 0.0700
Epoch 5/10
1000/1000 [==============================] - 0s 73us/step - loss: 11.5181 - categorical_accuracy: 0.1150 - val_loss: 11.0184 - val_categorical_accuracy: 0.0500
Epoch 6/10
1000/1000 [==============================] - 0s 72us/step - loss: 11.5177 - categorical_accuracy: 0.1150 - val_loss: 10.9892 - val_categorical_accuracy: 0.0200
Epoch 7/10
1000/1000 [==============================] - 0s 72us/step - loss: 11.5130 - categorical_accuracy: 0.1320 - val_loss: 11.0038 - val_categorical_accuracy: 0.0500
Epoch 8/10
1000/1000 [==============================] - 0s 74us/step - loss: 11.5123 - categorical_accuracy: 0.1130 - val_loss: 11.0065 - val_categorical_accuracy: 0.0100
Epoch 9/10
1000/1000 [==============================] - 0s 72us/step - loss: 11.5076 - categorical_accuracy: 0.1150 - val_loss: 11.0062 - val_categorical_accuracy: 0.0800
Epoch 10/10
1000/1000 [==============================] - 0s 67us/step - loss: 11.5035 - categorical_accuracy: 0.1390 - val_loss: 11.0241 - val_categorical_accuracy: 0.1100使用?Datasets API?可擴(kuò)展為大型數(shù)據(jù)集或多設(shè)備訓(xùn)練。將?tf.data.Dataset?實(shí)例傳遞到?fit?方法：
# 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)
Epoch 1/10
30/30 [==============================] - 0s 6ms/step - loss: 11.4973 - categorical_accuracy: 0.1406
Epoch 2/10
30/30 [==============================] - 0s 2ms/step - loss: 11.5182 - categorical_accuracy: 0.1344
Epoch 3/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4953 - categorical_accuracy: 0.1344
Epoch 4/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4842 - categorical_accuracy: 0.1542
Epoch 5/10
30/30 [==============================] - 0s 2ms/step - loss: 11.5081 - categorical_accuracy: 0.1510
Epoch 6/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4939 - categorical_accuracy: 0.1615
Epoch 7/10
30/30 [==============================] - 0s 2ms/step - loss: 11.5049 - categorical_accuracy: 0.1823
Epoch 8/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4617 - categorical_accuracy: 0.1760
Epoch 9/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4863 - categorical_accuracy: 0.1688
Epoch 10/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4946 - categorical_accuracy: 0.1885在上方代碼中，fit 方法使用了 steps_per_epoch 參數(shù)（表示模型在進(jìn)入下一個周期之前運(yùn)行的訓(xùn)練步數(shù)）。由于 Dataset 會生成批次數(shù)據(jù)，因此該代碼段不需要 batch_size。
數(shù)據(jù)集也可用于驗(yàn)證：
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)
Epoch 1/10
30/30 [==============================] - 0s 8ms/step - loss: 11.4649 - categorical_accuracy: 0.1740 - val_loss: 11.0269 - val_categorical_accuracy: 0.0521
Epoch 2/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4794 - categorical_accuracy: 0.1865 - val_loss: 11.4233 - val_categorical_accuracy: 0.0521
Epoch 3/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4604 - categorical_accuracy: 0.1760 - val_loss: 11.4040 - val_categorical_accuracy: 0.0208
Epoch 4/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4475 - categorical_accuracy: 0.1771 - val_loss: 11.3095 - val_categorical_accuracy: 0.2396
Epoch 5/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4727 - categorical_accuracy: 0.1750 - val_loss: 11.0481 - val_categorical_accuracy: 0.0938
Epoch 6/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4569 - categorical_accuracy: 0.1833 - val_loss: 11.3550 - val_categorical_accuracy: 0.1562
Epoch 7/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4653 - categorical_accuracy: 0.1958 - val_loss: 11.4325 - val_categorical_accuracy: 0.0417
Epoch 8/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4246 - categorical_accuracy: 0.1823 - val_loss: 11.3625 - val_categorical_accuracy: 0.0417
Epoch 9/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4542 - categorical_accuracy: 0.1729 - val_loss: 11.0326 - val_categorical_accuracy: 0.0521
Epoch 10/10
30/30 [==============================] - 0s 2ms/step - loss: 11.4600 - categorical_accuracy: 0.1979 - val_loss: 11.3494 - val_categorical_accuracy: 0.1042tf.keras.Model.evaluate?和?tf.keras.Model.predict?方法可以使用 NumPy 數(shù)據(jù)和?tf.data.Dataset。
要評估所提供數(shù)據(jù)的推理模式損失和指標(biāo)，請運(yùn)行以下代碼：
data = np.random.random((1000, 32))
labels = np.random.random((1000, 10))
model.evaluate(data, labels, batch_size=32)
model.evaluate(dataset, steps=30)
1000/1000 [==============================] - 0s 83us/step
30/30 [==============================] - 0s 3ms/step
[11.43181880315145, 0.18333333333333332]要在所提供數(shù)據(jù)（采用 NumPy 數(shù)組形式）的推理中預(yù)測最后一層的輸出，請運(yùn)行以下代碼：
result = model.predict(data, batch_size=32)
print(result.shape)
(1000, 10)tf.keras.Sequential?模型是層的簡單堆疊，無法表示任意模型。使用?Keras 函數(shù)式 API?可以構(gòu)建復(fù)雜的模型拓?fù)洌纾?/p>
使用函數(shù)式 API 構(gòu)建的模型具有以下特征：
以下示例使用函數(shù)式 API 構(gòu)建一個簡單的全連接網(wǎng)絡(luò)：
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)在給定輸入和輸出的情況下實(shí)例化模型。
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)
Epoch 1/5
1000/1000 [==============================] - 0s 260us/step - loss: 11.7190 - acc: 0.1080
Epoch 2/5
1000/1000 [==============================] - 0s 75us/step - loss: 11.5347 - acc: 0.1010
Epoch 3/5
1000/1000 [==============================] - 0s 74us/step - loss: 11.5020 - acc: 0.1100
Epoch 4/5
1000/1000 [==============================] - 0s 75us/step - loss: 11.4908 - acc: 0.1090
Epoch 5/5
1000/1000 [==============================] - 0s 74us/step - loss: 11.4809 - acc: 0.1330通過對 tf.keras.Model 進(jìn)行子類化并定義您自己的前向傳播來構(gòu)建完全可自定義的模型。在 __init__ 方法中創(chuàng)建層并將它們設(shè)置為類實(shí)例的屬性。在 call 方法中定義前向傳播。
在啟用 Eager Execution 時，模型子類化特別有用，因?yàn)榭梢悦钍降鼐帉懬跋騻鞑ァ?/p>
要點(diǎn)：針對作業(yè)使用正確的 API。雖然模型子類化較為靈活，但代價是復(fù)雜性更高且用戶出錯率更高。如果可能，請首選函數(shù)式 API。
以下示例展示了使用自定義前向傳播進(jìn)行子類化的?tf.keras.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)
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)
實(shí)例化新模型類：
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)
Epoch 1/5
1000/1000 [==============================] - 0s 224us/step - loss: 11.5206 - acc: 0.0990
Epoch 2/5
1000/1000 [==============================] - 0s 62us/step - loss: 11.5128 - acc: 0.1070
Epoch 3/5
1000/1000 [==============================] - 0s 64us/step - loss: 11.5023 - acc: 0.0980
Epoch 4/5
1000/1000 [==============================] - 0s 65us/step - loss: 11.4941 - acc: 0.0980
Epoch 5/5
1000/1000 [==============================] - 0s 66us/step - loss: 11.4879 - acc: 0.0990通過對?tf.keras.layers.Layer?進(jìn)行子類化并實(shí)現(xiàn)以下方法來創(chuàng)建自定義層：
下面是一個使用核矩陣實(shí)現(xiàn)輸入?matmul?的自定義層示例：
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)
# Be sure to call this 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)使用自定義層創(chuàng)建模型：
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)
Epoch 1/5
1000/1000 [==============================] - 0s 170us/step - loss: 11.4872 - acc: 0.0990
Epoch 2/5
1000/1000 [==============================] - 0s 52us/step - loss: 11.4817 - acc: 0.0910
Epoch 3/5
1000/1000 [==============================] - 0s 52us/step - loss: 11.4800 - acc: 0.0960
Epoch 4/5
1000/1000 [==============================] - 0s 57us/step - loss: 11.4778 - acc: 0.0960
Epoch 5/5
1000/1000 [==============================] - 0s 60us/step - loss: 11.4764 - acc: 0.0930回調(diào)是傳遞給模型的對象，用于在訓(xùn)練期間自定義該模型并擴(kuò)展其行為。您可以編寫自定義回調(diào)，也可以使用包含以下方法的內(nèi)置?tf.keras.callbacks：
要使用?tf.keras.callbacks.Callback，請將其傳遞給模型的?fit?方法：
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))
Train on 1000 samples, validate on 100 samples
Epoch 1/5
1000/1000 [==============================] - 0s 150us/step - loss: 11.4748 - acc: 0.1230 - val_loss: 10.9787 - val_acc: 0.1000
Epoch 2/5
1000/1000 [==============================] - 0s 78us/step - loss: 11.4730 - acc: 0.1060 - val_loss: 10.9783 - val_acc: 0.1300
Epoch 3/5
1000/1000 [==============================] - 0s 82us/step - loss: 11.4711 - acc: 0.1130 - val_loss: 10.9756 - val_acc: 0.1500
Epoch 4/5
1000/1000 [==============================] - 0s 82us/step - loss: 11.4704 - acc: 0.1050 - val_loss: 10.9772 - val_acc: 0.0900
Epoch 5/5
1000/1000 [==============================] - 0s 83us/step - loss: 11.4689 - acc: 0.1140 - val_loss: 10.9781 - val_acc: 0.1300使用?tf.keras.Model.save_weights?保存并加載模型的權(quán)重：
model = tf.keras.Sequential([
layers.Dense(64, activation='relu'),
layers.Dense(10, activation='softmax')])
model.compile(optimizer=tf.train.AdamOptimizer(0.001),
loss='categorical_crossentropy',
metrics=['accuracy'])
# Save weights to a TensorFlow Checkpoint file
model.save_weights('./weights/my_model')
# Restore the model's state,
# this requires a model with the same architecture.
model.load_weights('./weights/my_model')默認(rèn)情況下，會以?TensorFlow 檢查點(diǎn)文件格式保存模型的權(quán)重。權(quán)重也可以另存為 Keras HDF5 格式（Keras 多后端實(shí)現(xiàn)的默認(rèn)格式）：
# 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')可以保存模型的配置，此操作會對模型架構(gòu)（不含任何權(quán)重）進(jìn)行序列化。即使沒有定義原始模型的代碼，保存的配置也可以重新創(chuàng)建并初始化相同的模型。Keras 支持 JSON 和 YAML 序列化格式：
# Serialize a model to JSON format
json_string = model.to_json()
json_string
'{"backend": "tensorflow", "keras_version": "2.1.6-tf", "config": {"name": "sequential_3", "layers": [{"config": {"units": 64, "kernel_regularizer": null, "activation": "relu", "bias_constraint": null, "trainable": true, "use_bias": true, "bias_initializer": {"config": {"dtype": "float32"}, "class_name": "Zeros"}, "activity_regularizer": null, "dtype": null, "kernel_constraint": null, "kernel_initializer": {"config": {"mode": "fan_avg", "seed": null, "distribution": "uniform", "scale": 1.0, "dtype": "float32"}, "class_name": "VarianceScaling"}, "name": "dense_17", "bias_regularizer": null}, "class_name": "Dense"}, {"config": {"units": 10, "kernel_regularizer": null, "activation": "softmax", "bias_constraint": null, "trainable": true, "use_bias": true, "bias_initializer": {"config": {"dtype": "float32"}, "class_name": "Zeros"}, "activity_regularizer": null, "dtype": null, "kernel_constraint": null, "kernel_initializer": {"config": {"mode": "fan_avg", "seed": null, "distribution": "uniform", "scale": 1.0, "dtype": "float32"}, "class_name": "VarianceScaling"}, "name": "dense_18", "bias_regularizer": null}, "class_name": "Dense"}]}, "class_name": "Sequential"}'
import json
import pprint
pprint.pprint(json.loads(json_string))
{'backend': 'tensorflow',
'class_name': 'Sequential',
'config': {'layers': [{'class_name': 'Dense',
'config': {'activation': 'relu',
'activity_regularizer': None,
'bias_constraint': None,
'bias_initializer': {'class_name': 'Zeros',
'config': {'dtype': 'float32'}},
'bias_regularizer': None,
'dtype': None,
'kernel_constraint': None,
'kernel_initializer': {'class_name': 'VarianceScaling',
'config': {'distribution': 'uniform',
'dtype': 'float32',
'mode': 'fan_avg',
'scale': 1.0,
'seed': None}},
'kernel_regularizer': None,
'name': 'dense_17',
'trainable': True,
'units': 64,
'use_bias': True}},
{'class_name': 'Dense',
'config': {'activation': 'softmax',
'activity_regularizer': None,
'bias_constraint': None,
'bias_initializer': {'class_name': 'Zeros',
'config': {'dtype': 'float32'}},
'bias_regularizer': None,
'dtype': None,
'kernel_constraint': None,
'kernel_initializer': {'class_name': 'VarianceScaling',
'config': {'distribution': 'uniform',
'dtype': 'float32',
'mode': 'fan_avg',
'scale': 1.0,
'seed': None}},
'kernel_regularizer': None,
'name': 'dense_18',
'trainable': True,
'units': 10,
'use_bias': True}}],
'name': 'sequential_3'},
'keras_version': '2.1.6-tf'}從 json 重新創(chuàng)建模型（剛剛初始化）
fresh_model = tf.keras.models.model_from_json(json_string)
將模型序列化為 YAML 格式
backend: tensorflow
class_name: Sequential
config:
layers:
- class_name: Dense
config:
activation: relu
activity_regularizer: null
bias_constraint: null
bias_initializer:
class_name: Zeros
config: {dtype: float32}
bias_regularizer: null
dtype: null
kernel_constraint: null
kernel_initializer:
class_name: VarianceScaling
config: {distribution: uniform, dtype: float32, mode: fan_avg, scale: 1.0,
seed: null}
kernel_regularizer: null
name: dense_17
trainable: true
units: 64
use_bias: true
- class_name: Dense
config:
activation: softmax
activity_regularizer: null
bias_constraint: null
bias_initializer:
class_name: Zeros
config: {dtype: float32}
bias_regularizer: null
dtype: null
kernel_constraint: null
kernel_initializer:
class_name: VarianceScaling
config: {distribution: uniform, dtype: float32, mode: fan_avg, scale: 1.0,
seed: null}
kernel_regularizer: null
name: dense_18
trainable: true
units: 10
use_bias: true
name: sequential_3
keras_version: 2.1.6-tf從 yaml 重新創(chuàng)建模型
fresh_model = tf.keras.models.model_from_yaml(yaml_string)
注意：子類化模型不可序列化，因?yàn)樗鼈兊募軜?gòu)由 call 方法正文中的 Python 代碼定義。
整個模型
整個模型可以保存到一個文件中，其中包含權(quán)重值、模型配置乃至優(yōu)化器配置。這樣，您就可以對模型設(shè)置檢查點(diǎn)并稍后從完全相同的狀態(tài)繼續(xù)訓(xùn)練，而無需訪問原始代碼。
# 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')
Epoch 1/5
1000/1000 [==============================] - 0s 297us/step - loss: 11.5009 - acc: 0.0980
Epoch 2/5
1000/1000 [==============================] - 0s 76us/step - loss: 11.4844 - acc: 0.0960
Epoch 3/5
1000/1000 [==============================] - 0s 77us/step - loss: 11.4791 - acc: 0.0850
Epoch 4/5
1000/1000 [==============================] - 0s 78us/step - loss: 11.4771 - acc: 0.1020
Epoch 5/5
1000/1000 [==============================] - 0s 79us/step - loss: 11.4763 - acc: 0.0900Eager Execution?是一種命令式編程環(huán)境，可立即評估操作。此環(huán)境對于 Keras 并不是必需的，但是受?tf.keras?的支持，并且可用于檢查程序和調(diào)試。
所有 tf.keras 模型構(gòu)建 API 都與 Eager Execution 兼容。雖然可以使用 Sequential 和函數(shù)式 API，但 Eager Execution 對模型子類化和構(gòu)建自定義層特別有用。與通過組合現(xiàn)有層來創(chuàng)建模型的 API 不同，函數(shù)式 API 要求您編寫前向傳播代碼。
請參閱 Eager Execution 指南，了解將 Keras 模型與自定義訓(xùn)練循環(huán)和 tf.GradientTape 搭配使用的示例（https://tensorflow.google.cn/guide/eager?hl=zh-CN#build_a_model）。
Estimator API 用于針對分布式環(huán)境訓(xùn)練模型。它適用于一些行業(yè)使用場景，例如用大型數(shù)據(jù)集進(jìn)行分布式訓(xùn)練并導(dǎo)出模型以用于生產(chǎn)。
tf.keras.Model?可以通過?tf.estimator?API 進(jìn)行訓(xùn)練，方法是將該模型轉(zhuǎn)換為?tf.estimator.Estimator?對象（通過?tf.keras.estimator.model_to_estimator）。請參閱用?Keras 模型創(chuàng)建 Estimator（https://tensorflow.google.cn/guide/estimators?hl=zh-CN#creating_estimators_from_keras_models）。
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)
INFO:tensorflow:Using the Keras model provided.
INFO:tensorflow:Using default config.
WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmpm0ljzq8s
INFO:tensorflow:Using config: {'_experimental_distribute': None, '_master': '', '_eval_distribute': None, '_num_ps_replicas': 0, '_protocol': None, '_global_id_in_cluster': 0, '_save_summary_steps': 100, '_tf_random_seed': None, '_model_dir': '/tmp/tmpm0ljzq8s', '_evaluation_master': '', '_task_id': 0, '_keep_checkpoint_max': 5, '_save_checkpoints_steps': None, '_service': None, '_num_worker_replicas': 1, '_save_checkpoints_secs': 600, '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x7fad8c5d3e10>, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_session_config': allow_soft_placement: true
graph_options {
rewrite_options {
meta_optimizer_iterations: ONE
}
}
, '_train_distribute': None, '_task_type': 'worker', '_device_fn': None}注意：請啟用 Eager Execution 以調(diào)試 Estimator 輸入函數(shù)并檢查數(shù)據(jù)。
tf.keras 模型可以使用 tf.contrib.distribute.DistributionStrategy 在多個 GPU 上運(yùn)行。此 API 在多個 GPU 上提供分布式訓(xùn)練，幾乎不需要更改現(xiàn)有代碼。
目前，tf.contrib.distribute.MirroredStrategy?是唯一受支持的分布策略。MirroredStrategy?通過在一臺機(jī)器上使用規(guī)約在同步訓(xùn)練中進(jìn)行圖內(nèi)復(fù)制。要將?DistributionStrategy?與 Keras 搭配使用，請將?tf.keras.Model?轉(zhuǎn)換為?tf.estimator.Estimator（通過?tf.keras.estimator.model_to_estimator），然后訓(xùn)練該 Estimator
以下示例在一臺機(jī)器上的多個 GPU 間分布了 tf.keras.Model。
首先，定義一個簡單的模型：
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()
# Import libraries for simulation
import tensorflow as tf
import numpy as np
# Imports for visualization
import PIL.Image
from io import BytesIO
from IPython.display import Image, display
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_23 (Dense) (None, 16) 176
_________________________________________________________________
dense_24 (Dense) (None, 1) 17
=================================================================
Total params: 193
Trainable params: 193
Non-trainable params: 0
_________________________________________________________________定義輸入管道。input_fn?會返回?tf.data.Dataset?對象，此對象用于將數(shù)據(jù)分布在多臺設(shè)備上，每臺設(shè)備處理輸入批次數(shù)據(jù)的一部分。
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接下來，創(chuàng)建?tf.estimator.RunConfig?并將?train_distribute?參數(shù)設(shè)置為?tf.contrib.distribute.MirroredStrategy?實(shí)例。創(chuàng)建?MirroredStrategy?時，您可以指定設(shè)備列表或設(shè)置?num_gpus?參數(shù)。默認(rèn)使用所有可用的 GPU，如下所示：
strategy = tf.contrib.distribute.MirroredStrategy()
config = tf.estimator.RunConfig(train_distribute=strategy)
INFO:tensorflow:Initializing RunConfig with distribution strategies.
INFO:tensorflow:Not using Distribute Coordinator.
將 Keras 模型轉(zhuǎn)換為?tf.estimator.Estimator?實(shí)例：
keras_estimator = tf.keras.estimator.model_to_estimator(
keras_model=model,
config=config,
model_dir='/tmp/model_dir')
INFO:tensorflow:Using the Keras model provided.
INFO:tensorflow:Using config: {'_experimental_distribute': None, '_master': '', '_eval_distribute': None, '_num_ps_replicas': 0, '_protocol': None, '_global_id_in_cluster': 0, '_save_summary_steps': 100, '_tf_random_seed': None, '_model_dir': '/tmp/model_dir', '_evaluation_master': '', '_task_id': 0, '_keep_checkpoint_max': 5, '_save_checkpoints_steps': None, '_service': None, '_num_worker_replicas': 1, '_save_checkpoints_secs': 600, '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x7faed9e1c550>, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_distribute_coordinator_mode': None, '_session_config': allow_soft_placement: true
graph_options {
rewrite_options {
meta_optimizer_iterations: ONE最后，通過提供?input_fn?和?steps?參數(shù)訓(xùn)練?Estimator?實(shí)例：
keras_estimator.train(input_fn=input_fn, steps=10)
WARNING:tensorflow:Not all devices in DistributionStrategy are visible to TensorFlow session.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Warm-starting with WarmStartSettings: WarmStartSettings(ckpt_to_initialize_from='/tmp/model_dir/keras/keras_model.ckpt', vars_to_warm_start='.*', var_name_to_vocab_info={}, var_name_to_prev_var_name={})
INFO:tensorflow:Warm-starting from: ('/tmp/model_dir/keras/keras_model.ckpt',)
INFO:tensorflow:Warm-starting variable: dense_24/kernel; prev_var_name: Unchanged
INFO:tensorflow:Warm-starting variable: dense_23/bias; prev_var_name: Unchanged
INFO:tensorflow:Warm-starting variable: dense_24/bias; prev_var_name: Unchanged
INFO:tensorflow:Warm-starting variable: dense_23/kernel; prev_var_name: Unchanged
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Saving checkpoints for 0 into /tmp/model_dir/model.ckpt.
INFO:tensorflow:Initialize system
INFO:tensorflow:loss = 0.7582453, step = 0
INFO:tensorflow:Saving checkpoints for 10 into /tmp/model_dir/model.ckpt.
INFO:tensorflow:Finalize system.
INFO:tensorflow:Loss for final step: 0.6743419.文章轉(zhuǎn)自微信公眾號@TensorFlow