兩種創建model的方式
1:鏈式函數創建
要創建輸入層inputs

import tensorflow as tfinputs = tf.keras.Input(shape=(3,))
x = tf.keras.layers.Dense(4, activation=tf.nn.relu)(inputs)
outputs = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)

2:使用對象創建

import tensorflow as tfclass MyModel(tf.keras.Model):def __init__(self):super(MyModel, self).__init__()self.dense1 = tf.keras.layers.Dense(4, activation=tf.nn.relu)self.dense2 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)def call(self, inputs):x = self.dense1(inputs)return self.dense2(x)model = MyModel()

屬性

方法

1. compile

compile(optimizer,loss=None,metrics=None,loss_weights=None,sample_weight_mode=None,weighted_metrics=None,target_tensors=None,distribute=None,**kwargs
)

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
)

evaluate_generator

evaluate_generator(generator,steps=None,callbacks=None,max_queue_size=10,workers=1,use_multiprocessing=False,verbose=0
)

fit

fit_generator

get_layer

get_layer(name=None,index=None
)

load_weights

load_weights(filepath,by_name=False
)

predict

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

predict_generator

predict_generator(generator,steps=None,callbacks=None,max_queue_size=10,workers=1,use_multiprocessing=False,verbose=0
)

predict_on_batch

predict_on_batch(x)

reset_metrics

reset_states

save

保存模型為HDF5文件

save_weights

summary

summary(line_length=None,positions=None,print_fn=None
)

test_on_batch

to_json

to_yaml

train_on_batch

tensorflow1，參考：
https://tensorflow.google.cn/versions/r2.0/api_docs/python/tf/keras/Model