tensorflow2自定義損失函數

一、總結

一句話總結：

直接定義函數，然后在compile時傳給loss即可

def customized_mse(y_true, y_pred):
    return tf.reduce_mean(tf.square(y_pred - y_true))

model = keras.models.Sequential([
    keras.layers.Dense(30, activation='relu',
                       input_shape=x_train.shape[1:]),
    keras.layers.Dense(1),
])
model.summary()
model.compile(loss=customized_mse, optimizer="sgd",
              metrics=["mean_squared_error"])

 

 

 

二、tensorflow2自定義損失函數

轉自或參考：tensorflow2.x學習筆記十七：自定義網絡層、模型以及損失函數
https://blog.csdn.net/qq_39507748/article/details/105256541

一、自定義網絡層layer

• 繼承tf.keras.layers.Layer類
• 使用tf.keras.layers.Lambda類

下面這個例子就包含了以上兩種形式：

from tensorflow import keras

class CustomizedDenseLayer(keras.layers.Layer):
    def __init__(self, units, activation=None, **kwargs):
        self.units = units
        self.activation = keras.layers.Activation(activation)
        super(CustomizedDenseLayer, self).__init__(**kwargs)
    
    def build(self, input_shape):
        """構建所需要的參數"""
        # x * w + b. input_shape:[None, a] w:[a,b]output_shape: [None, b]
        self.kernel = self.add_weight(name = 'kernel',
                                      shape = (input_shape[1], 
                                               self.units),
                                      initializer = 'uniform',
                                      trainable = True)
        self.bias = self.add_weight(name = 'bias',
                                    shape = (self.units, ),
                                    initializer = 'zeros',
                                    trainable = True)
        super(CustomizedDenseLayer, self).build(input_shape)
    
    def call(self, x):
        """完成正向計算"""
        return self.activation(x @ self.kernel + self.bias)

customized_softplus = keras.layers.Lambda(lambda x : tf.nn.softplus(x))

model = keras.models.Sequential([
    CustomizedDenseLayer(30, activation='relu',
                         input_shape=x_train.shape[1:]),
    CustomizedDenseLayer(1),
    customized_softplus,
])

二、自定義模型model

• 繼承tf.keras.Model類

import tensorflow as tf

class 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)
    self.dropout = tf.keras.layers.Dropout(0.5)

  def call(self, inputs, training=False):
     x = self.dense1(inputs)
     if training:
        x = self.dropout(x, training=training)
     return self.dense2(x)

model = MyModel()

三、自定義損失函數loss

直接定義函數，然后在compile時傳給loss參數即可

def customized_mse(y_true, y_pred):
    return tf.reduce_mean(tf.square(y_pred - y_true))

model = keras.models.Sequential([
    keras.layers.Dense(30, activation='relu',
                       input_shape=x_train.shape[1:]),
    keras.layers.Dense(1),
])
model.summary()
model.compile(loss=customized_mse, optimizer="sgd",
              metrics=["mean_squared_error"])