keras系列︱Sequential与Model模型、keras基本结构功能（一）

# 节点信息提取
config = model.get_config()  # 把model中的信息，solver.prototxt和train.prototxt信息提取出来
model = Model.from_config(config)  # 还回去
# or, for Sequential:
model = Sequential.from_config(config) # 重构一个新的Model模型，用去其他训练，fine-tuning比较好用

# 1、模型概括打印
model.summary()

# 2、返回代表模型的JSON字符串，仅包含网络结构，不包含权值。可以从JSON字符串中重构原模型：
from models import model_from_json

json_string = model.to_json()
model = model_from_json(json_string)

# 3、model.to_yaml：与model.to_json类似，同样可以从产生的YAML字符串中重构模型
from models import model_from_yaml

yaml_string = model.to_yaml()
model = model_from_yaml(yaml_string)

# 4、权重获取
model.get_layer()      #依据层名或下标获得层对象
model.get_weights()    #返回模型权重张量的列表，类型为numpy array
model.set_weights()    #从numpy array里将权重载入给模型，要求数组具有与model.get_weights()相同的形状。

# 查看model中Layer的信息
model.layers 查看layer信息

model.save_weights(filepath)
# 将模型权重保存到指定路径，文件类型是HDF5（后缀是.h5）

model.load_weights(filepath, by_name=False)
# 从HDF5文件中加载权重到当前模型中, 默认情况下模型的结构将保持不变。
# 如果想将权重载入不同的模型（有些层相同）中，则设置by_name=True，只有名字匹配的层才会载入权重

import tensorflow as tf
from keras.backend.tensorflow_backend import set_session
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.3
set_session(tf.Session(config=config))

filepath = 'model-ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5'
checkpoint = ModelCheckpoint(filepath, monitor='val_loss', verbose=1, save_best_only=True, mode='min')
# fit model
model.fit(x, y, epochs=20, verbose=2, callbacks=[checkpoint], validation_data=(x, y))

 ETA: 3s - loss: 0.5820Epoch 00017: val_loss did not improve

    RUN = RUN + 1 if 'RUN' in locals() else 1   # locals() 函数会以字典类型返回当前位置的全部局部变量。

    LOG_DIR = model_save_path + '/training_logs/run{}'.format(RUN)
    LOG_FILE_PATH = LOG_DIR + '/checkpoint-{epoch:02d}-{val_loss:.4f}.hdf5'   # 模型Log文件以及.h5模型文件存放地址

    tensorboard = TensorBoard(log_dir=LOG_DIR, write_images=True)
    checkpoint = ModelCheckpoint(filepath=LOG_FILE_PATH, monitor='val_loss', verbose=1, save_best_only=True)
    early_stopping = EarlyStopping(monitor='val_loss', patience=5, verbose=1)

    history = model.fit_generator(generator=gen.generate(True), steps_per_epoch=int(gen.train_batches / 4),
                                  validation_data=gen.generate(False), validation_steps=int(gen.val_batches / 4),
                                  epochs=EPOCHS, verbose=1, callbacks=[tensorboard, checkpoint, early_stopping])

add(self, layer)

# 譬如：
model.add(Dense(32, activation='relu', input_dim=100))
model.add(Dropout(0.25))

compile(self, optimizer, loss, metrics=None, sample_weight_mode=None)

fit(self, x, y, batch_size=32, epochs=10, verbose=1, callbacks=None, validation_split=0.0, validation_data=None, shuffle=True, class_weight=None, sample_weight=None, initial_epoch=0)

evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None)

predict(self, x, batch_size=32, verbose=0)
predict_classes(self, x, batch_size=32, verbose=1)
predict_proba(self, x, batch_size=32, verbose=1)

train_on_batch(self, x, y, class_weight=None, sample_weight=None)
test_on_batch(self, x, y, sample_weight=None)
predict_on_batch(self, x)

#利用Python的生成器，逐个生成数据的batch并进行训练。
#生成器与模型将并行执行以提高效率。
#例如，该函数允许我们在CPU上进行实时的数据提升，同时在GPU上进行模型训练
# 参考链接：http://keras-cn.readthedocs.io/en/latest/models/sequential/

fit_generator(self, generator, steps_per_epoch, epochs=1, verbose=1, callbacks=None, validation_data=None, validation_steps=None, class_weight=None, max_q_size=10, workers=1, pickle_safe=False, initial_epoch=0)
# 案例：
def generate_arrays_from_file(path):
while 1:
f = open(path)
for line in f:
# create Numpy arrays of input data
# and labels, from each line in the file
x, y = process_line(line)
yield (x, y)
f.close()
model.fit_generator(generate_arrays_from_file('/my_file.txt'),
samples_per_epoch=10000, epochs=10)

evaluate_generator(self, generator, steps, max_q_size=10, workers=1, pickle_safe=False)
predict_generator(self, generator, steps, max_q_size=10, workers=1, pickle_safe=False, verbose=0)

from keras.models import Sequential
from keras.layers import Dense, Activation

#模型搭建阶段
model= Sequential()
model.add(Dense(32, activation='relu', input_dim=100))
# Dense(32) is a fully-connected layer with 32 hidden units.
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])

# Generate dummy data
import numpy as np
data = np.random.random((1000, 100))
labels = np.random.randint(2, size=(1000, 1))
# Train the model, iterating on the data in batches of 32 samples
model.fit(data, labels, nb_epoch =10, batch_size=32)

 error:
TypeError: Received unknown keyword arguments: {'epochs': 10}

import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.optimizers import SGD
from keras.utils import np_utils
# Generate dummy data
x_train = np.random.random((100, 100, 100, 3))
# 100张图片，每张100*100*3
y_train = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
# 100*10
x_test = np.random.random((20, 100, 100, 3))
y_test = keras.utils.to_categorical(np.random.randint(10, size=(20, 1)), num_classes=10)
# 20*100
model = Sequential()
# input: 100x100 images with 3 channels -> (100, 100, 3) tensors.
# this applies 32 convolution filters of size 3x3 each.
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(100, 100, 3)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
model.fit(x_train, y_train, batch_size=32, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=32)

keras.utils.to_categorical

from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import Embedding
from keras.layers import LSTM
model = Sequential()
model.add(Embedding(max_, output_dim=256))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=16, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=16)

model.layers：组成模型图的各个层
model.inputs：模型的输入张量列表
model.outputs：模型的输出张量列表

compile(self, optimizer, loss, metrics=None, loss_weights=None, sample_weight_mode=None)

fit(self, x=None, y=None, batch_size=32, epochs=1, verbose=1, callbacks=None, validation_split=0.0, validation_data=None, shuffle=True, class_weight=None, sample_weight=None, initial_epoch=0)

evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None)

predict(self, x, batch_size=32, verbose=0)

train_on_batch(self, x, y, class_weight=None, sample_weight=None)
test_on_batch(self, x, y, sample_weight=None)
predict_on_batch(self, x)

fit_generator(self, generator, steps_per_epoch, epochs=1, verbose=1, callbacks=None, validation_data=None, validation_steps=None, class_weight=None, max_q_size=10, workers=1, pickle_safe=False, initial_epoch=0)
evaluate_generator(self, generator, steps, max_q_size=10, workers=1, pickle_safe=False)

from keras.layers import Input, Dense
from keras.models import Model
# This returns a tensor
inputs = Input(shape=(784,))
# a layer instance is callable on a tensor, and returns a tensor
x = Dense(64, activation='relu')(inputs)
# 输入inputs，输出x
# (inputs)代表输入
x = Dense(64, activation='relu')(x)
# 输入x，输出x
predictions = Dense(10, activation='softmax')(x)
# 输入x，输出分类
# This creates a model that includes
# the Input layer and three Dense layers
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(data, labels)  # starts training

x = Input(shape=(784,))
# This works, and returns the 10-way softmax we defined above.
y = model(x)
# model里面存着权重，然后输入x，输出结果，用来作fine-tuning
# 分类->视频、实时处理
from keras.layers import TimeDistributed
# Input tensor for sequences of 20 timesteps,
# each containing a 784-dimensional vector
input_sequences = Input(shape=(20, 784))
# 20个时间间隔，输入784维度的数据
# This applies our previous model to every timestep in the input sequences.
# the output of the previous model was a 10-way softmax,
# so the output of the layer below will be a sequence of 20 vectors of size 10.
processed_sequences = TimeDistributed(model)(input_sequences)
# Model是已经训练好的

from keras.layers import Input, Embedding, LSTM, Dense
from keras.models import Model
# Headline input: meant to receive sequences of 100 integers, between 1 and 10000.
# Note that we can name any layer by passing it a "name" argument.
main_input = Input(shape=(100,), dtype='int32', name='main_input')
# 一个100词的BOW序列
# This embedding layer will encode the input sequence
# into a sequence of dense 512-dimensional vectors.
x = Embedding(output_dim=512, input_dim=10000, input_length=100)(main_input)
# Embedding层，把100维度再encode成512的句向量，10000指的是词典单词总数
# A LSTM will transform the vector sequence into a single vector,
# containing information about the entire sequence
lstm_out = LSTM(32)(x)
# ？ 32什么意思？？？？？？？？？？？？？？？？？？？？？
#然后，我们插入一个额外的损失，使得即使在主损失很高的情况下，LSTM和Embedding层也可以平滑的训练。
auxiliary_output = Dense(1, activation='sigmoid', name='aux_output')(lstm_out)
#再然后，我们将LSTM与额外的输入数据串联起来组成输入，送入模型中：
# 模型一：只针对以上的序列做的预测模型

# 模型二：组合模型
auxiliary_input = Input(shape=(5,), name='aux_input')  # 新加入的一个Input,5维度
x = keras.layers.concatenate([lstm_out, auxiliary_input])   # 组合起来，对应起来
# We stack a deep densely-connected network on top
# 组合模型的形式
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
# And finally we add the main logistic regression layer
main_output = Dense(1, activation='sigmoid', name='main_output')(x)
#最后，我们定义整个2输入，2输出的模型：
model = Model(inputs=[main_input, auxiliary_input], outputs=[main_output, auxiliary_output])
#模型定义完毕，下一步编译模型。
#我们给额外的损失赋0.2的权重。我们可以通过关键字参数loss_weights或loss来为不同的输出设置不同的损失函数或权值。
#这两个参数均可为Python的列表或字典。这里我们给loss传递单个损失函数，这个损失函数会被应用于所有输出上。

# 训练方式一：两个模型一个loss
model.compile(optimizer='rmsprop', loss='binary_crossentropy',
loss_weights=[1., 0.2])
#编译完成后，我们通过传递训练数据和目标值训练该模型：
model.fit([headline_data, additional_data], [labels, labels],
epochs=50, batch_size=32)
# 训练方式二：两个模型,两个Loss
#因为我们输入和输出是被命名过的（在定义时传递了“name”参数），我们也可以用下面的方式编译和训练模型：
model.compile(optimizer='rmsprop',
loss={ 
'main_output': 'binary_crossentropy', 'aux_output': 'binary_crossentropy'},
loss_weights={ 
'main_output': 1., 'aux_output': 0.2})
# And trained it via:
model.fit({ 
'main_input': headline_data, 'aux_input': additional_data},
{ 
'main_output': labels, 'aux_output': labels},
epochs=50, batch_size=32)

import keras
from keras.layers import Input, LSTM, Dense
from keras.models import Model
tweet_a = Input(shape=(140, 256))
tweet_b = Input(shape=(140, 256))
#若要对不同的输入共享同一层，就初始化该层一次，然后多次调用它
# 140个单词，每个单词256维度，词向量
# 
# This layer can take as input a matrix
# and will return a vector of size 64
shared_lstm = LSTM(64)
# 返回一个64规模的向量
# When we reuse the same layer instance
# multiple times, the weights of the layer
# are also being reused
# (it is effectively *the same* layer)
encoded_a = shared_lstm(tweet_a)
encoded_b = shared_lstm(tweet_b)
# We can then concatenate the two vectors:
# 连接两个结果
# axis=-1？？？？？
merged_vector = keras.layers.concatenate([encoded_a, encoded_b], axis=-1)
# And add a logistic regression on top
predictions = Dense(1, activation='sigmoid')(merged_vector)
# 其中的1 代表什么？？？？
# We define a trainable model linking the
# tweet inputs to the predictions
model = Model(inputs=[tweet_a, tweet_b], outputs=predictions)
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit([data_a, data_b], labels, epochs=10)
# 训练模型，然后预测

# 1、单节点
a = Input(shape=(140, 256))
lstm = LSTM(32)
encoded_a = lstm(a)
assert lstm.output == encoded_a
# 抽取获得encoded_a的输出张量
# 2、多节点
a = Input(shape=(140, 256))
b = Input(shape=(140, 256))
lstm = LSTM(32)
encoded_a = lstm(a)
encoded_b = lstm(b)
assert lstm.get_output_at(0) == encoded_a
assert lstm.get_output_at(1) == encoded_b
# 3、图像层节点
# 对于input_shape和output_shape也是一样，如果一个层只有一个节点，
#或所有的节点都有相同的输入或输出shape，
#那么input_shape和output_shape都是没有歧义的，并也只返回一个值。
#但是，例如你把一个相同的Conv2D应用于一个大小为(3,32,32)的数据，
#然后又将其应用于一个(3,64,64)的数据，那么此时该层就具有了多个输入和输出的shape，
#你就需要显式的指定节点的下标，来表明你想取的是哪个了
a = Input(shape=(3, 32, 32))
b = Input(shape=(3, 64, 64))
conv = Conv2D(16, (3, 3), padding='same')
conved_a = conv(a)
# Only one input so far, the following will work:
assert conv.input_shape == (None, 3, 32, 32)
conved_b = conv(b)
# now the `.input_shape` property wouldn't work, but this does:
assert conv.get_input_shape_at(0) == (None, 3, 32, 32)
assert conv.get_input_shape_at(1) == (None, 3, 64, 64)

#这个模型将自然语言的问题和图片分别映射为特征向量，
#将二者合并后训练一个logistic回归层，从一系列可能的回答中挑选一个。
from keras.layers import Conv2D, MaxPooling2D, Flatten
from keras.layers import Input, LSTM, Embedding, Dense
from keras.models import Model, Sequential
# First, let's define a vision model using a Sequential model.
# This model will encode an image into a vector.
vision_model = Sequential()
vision_model.add(Conv2D(64, (3, 3) activation='relu', padding='same', input_shape=(3, 224, 224)))
vision_model.add(Conv2D(64, (3, 3), activation='relu'))
vision_model.add(MaxPooling2D((2, 2)))
vision_model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
vision_model.add(Conv2D(128, (3, 3), activation='relu'))
vision_model.add(MaxPooling2D((2, 2)))
vision_model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
vision_model.add(Conv2D(256, (3, 3), activation='relu'))
vision_model.add(Conv2D(256, (3, 3), activation='relu'))
vision_model.add(MaxPooling2D((2, 2)))
vision_model.add(Flatten())
# Now let's get a tensor with the output of our vision model:
image_input = Input(shape=(3, 224, 224))
encoded_image = vision_model(image_input)
# Next, let's define a language model to encode the question into a vector.
# Each question will be at most 100 word long,
# and we will index words as integers from 1 to 9999.
question_input = Input(shape=(100,), dtype='int32')
embedded_question = Embedding(input_dim=10000, output_dim=256, input_length=100)(question_input)
encoded_question = LSTM(256)(embedded_question)
# Let's concatenate the question vector and the image vector:
merged = keras.layers.concatenate([encoded_question, encoded_image])
# And let's train a logistic regression over 1000 words on top:
output = Dense(1000, activation='softmax')(merged)
# This is our final model:
vqa_model = Model(inputs=[image_input, question_input], outputs=output)
# The next stage would be training this model on actual data.

    model = Sequential()
model.add(Dense(2, input_dim=3, name="dense_1"))
model.add(Dense(3, name="dense_2"))
...
model.save_weights(fname)

# new model
model = Sequential()
model.add(Dense(2, input_dim=3, name="dense_1"))  # will be loaded
model.add(Dense(10, name="new_dense"))  # will not be loaded
# load weights from first model; will only affect the first layer, dense_1.
model.load_weights(fname, by_name=True)

cw = {0: 1, 1: 50}
model.fit(x_train, y_train,batch_size=batch_size,epochs=epochs,verbose=1,callbacks=cbks,validation_data=(x_test, y_test), shuffle=True,class_weight=cw)

from sklearn.utils import class_weight
list_classes = ["toxic", "severe_toxic", "obscene", "threat", "insult", "identity_hate"]
y = train[list_classes].values
sample_weights = class_weight.compute_sample_weight('balanced', y)
model.fit(X_t, y, batch_size=batch_size, epochs=epochs,validation_split=0.1,sample_weight=sample_weights, callbacks=callbacks_list)