TensorFlow2.0教程-keras 函數(shù)api

完整tensorflow2.0教程代碼請看tensorflow2.0：中文教程tensorflow2_tutorials_chinese(歡迎star)

# !pip install pydot
#!sudo apt-get install graphvizf

from __future__ import absolute_import, division, print_function
import tensorflow as tf
import tensorflow.keras as keras
import tensorflow.keras.layers as layers
tf.keras.backend.clear_session()

1構(gòu)建簡單的網(wǎng)絡(luò)

1.1創(chuàng)建網(wǎng)絡(luò)

inputs = tf.keras.Input(shape=(784,), name='img')
h1 = layers.Dense(32, activation='relu')(inputs)
h2 = layers.Dense(32, activation='relu')(h1)
outputs = layers.Dense(10, activation='softmax')(h2)
model = tf.keras.Model(inputs=inputs, outputs=outputs, name='mnist model')

model.summary()
keras.utils.plot_model(model, 'mnist_model.png')
keras.utils.plot_model(model, 'model_info.png', show_shapes=True)

1.2訓(xùn)練关霸、驗證及測試

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train = x_train.reshape(60000, 784).astype('float32') /255
x_test = x_test.reshape(10000, 784).astype('float32') /255
model.compile(optimizer=keras.optimizers.RMSprop(),
             loss='sparse_categorical_crossentropy', # 直接填api半开，后面會報錯
             metrics=['accuracy'])
history = model.fit(x_train, y_train, batch_size=64, epochs=5, validation_split=0.2)
test_scores = model.evaluate(x_test, y_test, verbose=0)
print('test loss:', test_scores[0])
print('test acc:', test_scores[1])

1.3模型保持和序列化

model.save('model_save.h5')
del model
model = keras.models.load_model('model_save.h5')

2 使用共享網(wǎng)絡(luò)創(chuàng)建多個模型

在函數(shù)API中象浑，通過在圖層圖中指定其輸入和輸出來創(chuàng)建模型芋浮。 這意味著可以使用單個圖層圖來生成多個模型份汗。

# 編碼器網(wǎng)絡(luò)和自編碼器網(wǎng)絡(luò)

encode_input = keras.Input(shape=(28,28,1), name='img')
h1 = layers.Conv2D(16, 3, activation='relu')(encode_input)
h1 = layers.Conv2D(32, 3, activation='relu')(h1)
h1 = layers.MaxPool2D(3)(h1)
h1 = layers.Conv2D(32, 3, activation='relu')(h1)
h1 = layers.Conv2D(16, 3, activation='relu')(h1)
encode_output = layers.GlobalMaxPool2D()(h1)

encode_model = keras.Model(inputs=encode_input, outputs=encode_output, name='encoder')
encode_model.summary()

h2 = layers.Reshape((4, 4, 1))(encode_output)
h2 = layers.Conv2DTranspose(16, 3, activation='relu')(h2)
h2 = layers.Conv2DTranspose(32, 3, activation='relu')(h2)
h2 = layers.UpSampling2D(3)(h2)
h2 = layers.Conv2DTranspose(16, 3, activation='relu')(h2)
decode_output = layers.Conv2DTranspose(1, 3, activation='relu')(h2)

autoencoder = keras.Model(inputs=encode_input, outputs=decode_output, name='autoencoder')
autoencoder.summary()

可以把整個模型怎憋，當作一層網(wǎng)絡(luò)使用

encode_input = keras.Input(shape=(28,28,1), name='src_img')
h1 = layers.Conv2D(16, 3, activation='relu')(encode_input)
h1 = layers.Conv2D(32, 3, activation='relu')(h1)
h1 = layers.MaxPool2D(3)(h1)
h1 = layers.Conv2D(32, 3, activation='relu')(h1)
h1 = layers.Conv2D(16, 3, activation='relu')(h1)
encode_output = layers.GlobalMaxPool2D()(h1)

encode_model = keras.Model(inputs=encode_input, outputs=encode_output, name='encoder')
encode_model.summary()

decode_input = keras.Input(shape=(16,), name='encoded_img')
h2 = layers.Reshape((4, 4, 1))(decode_input)
h2 = layers.Conv2DTranspose(16, 3, activation='relu')(h2)
h2 = layers.Conv2DTranspose(32, 3, activation='relu')(h2)
h2 = layers.UpSampling2D(3)(h2)
h2 = layers.Conv2DTranspose(16, 3, activation='relu')(h2)
decode_output = layers.Conv2DTranspose(1, 3, activation='relu')(h2)
decode_model = keras.Model(inputs=decode_input, outputs=decode_output, name='decoder')
decode_model.summary()

autoencoder_input = keras.Input(shape=(28,28,1), name='img')
h3 = encode_model(autoencoder_input)
autoencoder_output = decode_model(h3)
autoencoder = keras.Model(inputs=autoencoder_input, outputs=autoencoder_output,
                          name='autoencoder')
autoencoder.summary()

3.復(fù)雜網(wǎng)絡(luò)結(jié)構(gòu)構(gòu)建

3.1多輸入與多輸出網(wǎng)絡(luò)

# 構(gòu)建一個根據(jù)文檔內(nèi)容映跟、標簽和標題迹卢，預(yù)測文檔優(yōu)先級和執(zhí)行部門的網(wǎng)絡(luò)
# 超參
num_words = 2000
num_tags = 12
num_departments = 4

# 輸入
body_input = keras.Input(shape=(None,), name='body')
title_input = keras.Input(shape=(None,), name='title')
tag_input = keras.Input(shape=(num_tags,), name='tag')

# 嵌入層
body_feat = layers.Embedding(num_words, 64)(body_input)
title_feat = layers.Embedding(num_words, 64)(title_input)

# 特征提取層
body_feat = layers.LSTM(32)(body_feat)
title_feat = layers.LSTM(128)(title_feat)
features = layers.concatenate([title_feat,body_feat, tag_input])

# 分類層
priority_pred = layers.Dense(1, activation='sigmoid', name='priority')(features)
department_pred = layers.Dense(num_departments, activation='softmax', name='department')(features)


# 構(gòu)建模型
model = keras.Model(inputs=[body_input, title_input, tag_input],
                    outputs=[priority_pred, department_pred])
model.summary()
keras.utils.plot_model(model, 'multi_model.png', show_shapes=True)

model.compile(optimizer=keras.optimizers.RMSprop(1e-3),
             loss={'priority': 'binary_crossentropy',
                  'department': 'categorical_crossentropy'},
             loss_weights=[1., 0.2])

import numpy as np
# 載入輸入數(shù)據(jù)
title_data = np.random.randint(num_words, size=(1280, 10))
body_data = np.random.randint(num_words, size=(1280, 100))
tag_data = np.random.randint(2, size=(1280, num_tags)).astype('float32')
# 標簽
priority_label = np.random.random(size=(1280, 1))
department_label = np.random.randint(2, size=(1280, num_departments))
# 訓(xùn)練
history = model.fit(
    {'title': title_data, 'body':body_data, 'tag':tag_data},
    {'priority':priority_label, 'department':department_label},
    batch_size=32,
    epochs=5
)

3.2小型殘差網(wǎng)絡(luò)

inputs = keras.Input(shape=(32,32,3), name='img')
h1 = layers.Conv2D(32, 3, activation='relu')(inputs)
h1 = layers.Conv2D(64, 3, activation='relu')(h1)
block1_out = layers.MaxPooling2D(3)(h1)

h2 = layers.Conv2D(64, 3, activation='relu', padding='same')(block1_out)
h2 = layers.Conv2D(64, 3, activation='relu', padding='same')(h2)
block2_out = layers.add([h2, block1_out])

h3 = layers.Conv2D(64, 3, activation='relu', padding='same')(block2_out)
h3 = layers.Conv2D(64, 3, activation='relu', padding='same')(h3)
block3_out = layers.add([h3, block2_out])

h4 = layers.Conv2D(64, 3, activation='relu')(block3_out)
h4 = layers.GlobalMaxPool2D()(h4)
h4 = layers.Dense(256, activation='relu')(h4)
h4 = layers.Dropout(0.5)(h4)
outputs = layers.Dense(10, activation='softmax')(h4)

model = keras.Model(inputs, outputs, name='small resnet')
model.summary()
keras.utils.plot_model(model, 'small_resnet_model.png', show_shapes=True)

(x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data()
x_train = x_train.astype('float32') / 255
x_test = y_train.astype('float32') / 255
y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)

model.compile(optimizer=keras.optimizers.RMSprop(1e-3),
             loss='categorical_crossentropy',
             metrics=['acc'])
model.fit(x_train, y_train,
         batch_size=64,
         epochs=1,
         validation_split=0.2)

#model.predict(x_test, batch_size=32)

4.共享網(wǎng)絡(luò)層

share_embedding = layers.Embedding(1000, 64)

input1 = keras.Input(shape=(None,), dtype='int32')
input2 = keras.Input(shape=(None,), dtype='int32')

feat1 = share_embedding(input1)
feat2 = share_embedding(input2)

5.模型復(fù)用

from tensorflow.keras.applications import VGG16
vgg16=VGG16()

feature_list = [layer.output for layer in vgg16.layers]
feat_ext_model = keras.Model(inputs=vgg16.input, outputs=feature_list)

img = np.random.random((1, 224, 224, 3).astype('float32'))
ext_features = feat_ext_model(img)

6.自定義網(wǎng)絡(luò)層

# import tensorflow as tf
# import tensorflow.keras as keras
class MyDense(layers.Layer):
    def __init__(self, units=32):
        super(MyDense, self).__init__()
        self.units = units
    def build(self, input_shape):
        self.w = self.add_weight(shape=(input_shape[-1], self.units),
                                 initializer='random_normal',
                                 trainable=True)
        self.b = self.add_weight(shape=(self.units,),
                                 initializer='random_normal',
                                 trainable=True)
    def call(self, inputs):
        return tf.matmul(inputs, self.w) + self.b
    
    def get_config(self):
        return {'units': self.units}
    
inputs = keras.Input((4,))
outputs = MyDense(10)(inputs)
model = keras.Model(inputs, outputs)
config = model.get_config()
new_model = keras.Model.from_config(
config, custom_objects={'MyDense':MyDense}
)

# 在自定義網(wǎng)絡(luò)層調(diào)用其他網(wǎng)絡(luò)層

# 超參
time_step = 10
batch_size = 32
hidden_dim = 32
inputs_dim = 5

# 網(wǎng)絡(luò)
class MyRnn(layers.Layer):
    def __init__(self):
        super(MyRnn, self).__init__()
        self.hidden_dim = hidden_dim
        self.projection1 = layers.Dense(units=hidden_dim, activation='relu')
        self.projection2 = layers.Dense(units=hidden_dim, activation='relu')
        self.classifier = layers.Dense(1, activation='sigmoid')
    def call(self, inputs):
        outs = []
        states = tf.zeros(shape=[inputs.shape[0], self.hidden_dim])
        for t in range(inputs.shape[1]):
            x = inputs[:,t,:]
            h = self.projection1(x)
            y = h + self.projection2(states)
            states = y
            outs.append(y)
        # print(outs)
        features = tf.stack(outs, axis=1)
        print(features.shape)
        return self.classifier(features)

# 構(gòu)建網(wǎng)絡(luò)
inputs = keras.Input(batch_shape=(batch_size, time_step, inputs_dim))
x = layers.Conv1D(32, 3)(inputs)
print(x.shape)
outputs = MyRnn()(x)
model = keras.Model(inputs, outputs)


rnn_model = MyRnn()
_ = rnn_model(tf.zeros((1, 10, 5)))