About keras layer

introduction: https://keras.io/layers/about-keras-layers/

All Keras layers have a number of methods in common:

layer.get_weights(): returns the weights of the layer as a list of Numpy arrays.
layer.set_weights(weights): sets the weights of the layer from a list of Numpy arrays (with the same shapes as the output of get_weights).
layer.get_config(): returns a dictionary containing the configuration of the layer. The layer can be reinstantiated from its config via:
layer = Dense(32)
config = layer.get_config()
reconstructed_layer = Dense.from_config(config)
Or:

from keras import layers

config = layer.get_config()
layer = layers.deserialize({'class_name': layer.class.name,
'config': config})
If a layer has a single node (i.e. if it isn't a shared layer), you can get its input tensor, output tensor, input shape and output shape via:

layer.input
layer.output
layer.input_shape
layer.output_shape
If the layer has multiple nodes (see: the concept of layer node and shared layers), you can use the following methods:

layer.get_input_at(node_index)
layer.get_output_at(node_index)
layer.get_input_shape_at(node_index)
layer.get_output_shape_at(node_index)

About Keras model -- Sequential methods

keras典型框架
主要讲述了keras经典模型--Sequential模型中model的顺序创建连接方法。
另外keras训练基本套路，compile, fit, evaluate, predict.
指定模型Sequential( )
---->堆叠模块 .add( )
---->编译模型 .compile( )
---->在训练数据上迭代 .fit( )
---->评估 .evaluate( )
---->对新数据的预测 .predict( )

Sequential模型的methods
https://keras.io/models/sequential/

(1)compile
compile(optimizer, loss=None, metrics=None, loss_weights=None, sample_weight_mode=None, weighted_metrics=None, target_tensors=None)

description: Configures the model for training.

(2)fit

fit(x=None, y=None, batch_size=None, epochs=1, verbose=1, callbacks=None, validation_split=0.0,
validation_data=None, shuffle=True, class_weight=None, sample_weight=None, initial_epoch=0,
steps_per_epoch=None, validation_steps=None, validation_freq=1, max_queue_size=10, workers=1, use_multiprocessing=False)

description: Trains the model for a fixed number of epochs (iterations on a dataset).

Arguments:
x: Input data.
y: Target data.
batch_size: Integer or None. Number of samples per gradient update. If unspecified, batch_size will default to 32
epochs：整数，训练终止时的epoch值，训练将在达到该epoch值时停止，当没有设置initial_epoch时，它就是训练的总轮数，否则训练的总轮数为epochs - inital_epoch
verbose：日志显示，0为不在标准输出流输出日志信息，1为输出进度条记录，2为每个epoch输出一行记录
validation_split：0~1之间的浮点数，用来指定训练集的一定比例数据作为验证集。验证集将不参与训练，并在每个epoch结束后测试的模型的指标，如损失函数、精确度等。
注意，validation_split的划分在shuffle之前，因此如果你的数据本身是有序的，需要先手工打乱再指定validation_split，否则可能会出现验证集样本不均匀。
validation_data：形式为（X，y）的tuple，是指定的验证集。此参数将覆盖validation_spilt。
shuffle：布尔值或字符串，一般为布尔值，表示是否在训练过程中随机打乱输入样本的顺序。若为字符串“batch”，则是用来处理HDF5数据的特殊情况，它将在batch内部将数据打乱。

Reference:
https://blog.csdn.net/LuYi_WeiLin/article/details/88555813

(3)evaluate

evaluate(x=None, y=None, batch_size=None, verbose=1, sample_weight=None, steps=None, callbacks=None, max_queue_size=10, workers=1, use_multiprocessing=False)

description: Returns the loss value & metrics values for the model in test mode. Computation is done in batches.

Arguments:
x: Input data.
y: Target data.
batch_size: Integer or None. Number of samples per gradient update. If unspecified, batch_size will default to 32

Reference:

(4)predict
predict(x, batch_size=None, verbose=0, steps=None, callbacks=None, max_queue_size=10, workers=1, use_multiprocessing=False)

description: Generates output predictions for the input samples

Returns

Numpy array(s) of predictions.

（二）batch-xxx

(1)train_on_batch
train_on_batch(x, y, sample_weight=None, class_weight=None, reset_metrics=True)

description:
Arguments:
Reference:

About keras model

common methods and attributes:

model.layers -- a flattended list of the layers comprising the model
model.get_layer(self，name=None，index=None):依据层名或下标获得层对象
model.inputs -- the list of input tensors of the model
model.outputs -- the list of output tensors of the model

model.summary() -- a summary representation of your model. Shortcut for utils.print_summary

model.summary()

---

Layer (type) Output Shape Param #

dense_4 (Dense) (None, 7) 35

---

activation_4 (Activation) (None, 7) 0

---

dense_5 (Dense) (None, 13) 104

---

activation_5 (Activation) (None, 13) 0

---

dense_6 (Dense) (None, 5) 70

---

activation_6 (Activation) (None, 5) 0

Total params: 209
Trainable params: 209
Non-trainable params: 0

---

知识点：

1. 详解keras的model.summary()输出参数Param计算过程
   https://blog.csdn.net/ybdesire/article/details/85217688

model.get_config() -- returns a dict containing the configuration of the model.

model.get_weights() -- a list of all weight tensors in the model,as numpy arrays.
model.set_weights(weights) -- sets the values of the weights of the model, from a list of Numpy arrays.
The arrays in the list should have the same shape as those returned by get_weights()

model.to_json() returns a representation of the model as a JSON string. Note that the representation does not include the weights,
only the architecture. You can reinstantiate the same model (with reinitialized weights) from the JSON string via:

from keras.models import model_from_json

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