最近對tensorflow十分感興趣，所以想做一個系列來詳細講解tensorflow來。
本教程主要由tensorflow2.0官方教程的個人學習復現筆記整理而來，並借鑒了一些keras構造神經網絡的方法，中文講解，方便喜歡閱讀中文教程的朋友，tensorflow官方教程：https://www.tensorflow.org
1構建簡單的網絡
1.1創建網絡
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訓練、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，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 使用共享網絡創建多個模型
在函數API中，通過在圖層圖中指定其輸入和輸出來創建模型。 這意味着可以使用單個圖層圖來生成多個模型。
# 編碼器網絡和自編碼器網絡
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，當作一層網絡使用
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.復雜網絡結構構建
3.1多輸入與多輸出網絡
# 構建一個根據文檔內容、標簽和標題，預測文檔優先級和執行部門的網絡
# 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
# 載入輸入數據
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小型殘差網絡
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.共享網絡層
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.自定義網絡層
# 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}
)無錫人流多少錢 http://www.xaytsgyy.com/
# 在自定義網絡層調用其他網絡層
# 超參
time_step = 10
batch_size = 32
hidden_dim = 32
inputs_dim = 5
# 網絡
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)
# 構建網絡
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)))