tensorflow中得Sequential, Flatten,Dense, compile, fit函数构造

keras.Squential类继承了keras.Model类，在tensorflow2.0中的keras模块中提供很多方便的网络层，可以直接调用，包括keras.layers.Flatten, keras.layers.Dense等。

Sequential

# Sequential类的构造函数
def __init__(self, layers=None, name=None)

Flatten

# Flatten类的构造函数
def __init__(self, data_format=None, **kwargs)

Dense

# Dense类的构造函数的定义原型
def __init__(self, units, activation=None, use_bias=True, \
kernel_initializer='glorot_uniform', bias_initializer='zeros',\ 
kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None,\
kernel_constraint=None, bias_constraint=None, **kwargs)

compile

# compile()函数的定义原型
def compile(self, optimizer, loss=None, metrics=None, loss_weight=None,\
 			sample_weight_model=None,weight_metrics=None,target_tensors=None,\
 			distribute=None, **kwargs)

fit

# fit()函数的定义原型
 def fit(x=None, y=None, batch_size=None, epochs=1, verbose=1, callbacks=None,\
  		 validation_split=0., validation_data=None, shuffle=True, class_weight=None, \
  		 sample_weight=None, initial_epoch=0, step_per_epoch=None, \
  		 validation_steps=None, validation_freq=1, max_queue_size=10, workers=1,\
   		 use_multiprocessing=False, **kwargs)

---

函数里的每个参数我就不一一注释了，大家需要什么参数可以直接百度查