Keras的核心原则是逐步揭示复杂性，可以在保持相应的高级便利性的同时，对操作细节进行更多控制。当我们要自定义fit中的训练算法时，可以重写模型中的train_step方法，然后调用fit来训练模型。

import numpy as np
import tensorflow as tf
from tensorflow import keras
x = np.random.random((1000, 32))
y = np.random.random((1000, 1))
class CustomModel(keras.Model):
    tf.random.set_seed(100)
    def train_step(self, data):
        # Unpack the data. Its structure depends on your model and
        # on what you pass to `fit()`.
        x, y = data
 
        with tf.GradientTape() as tape:
            y_pred = self(x, training=True)  # Forward pass
            # Compute the loss value
            # (the loss function is configured in `compile()`)
            loss = self.compiled_loss(y, y_pred, regularization_losses=self.losses)
 
        # Compute gradients
        trainable_vars = self.trainable_variables
        gradients = tape.gradient(loss, trainable_vars)
        # Update weights
        self.optimizer.apply_gradients(zip(gradients, trainable_vars))
        # Update metrics (includes the metric that tracks the loss)
        self.compiled_metrics.update_state(y, y_pred)
        # Return a dict mapping metric names to current value
        return {m.name: m.result() for m in self.metrics}
     
 
 
# Construct and compile an instance of CustomModel
inputs = keras.Input(shape=(32,))
outputs = keras.layers.Dense(1)(inputs)
model = CustomModel(inputs, outputs)
model.compile(optimizer="adam", loss=tf.losses.MSE, metrics=["mae"])
 
# Just use `fit` as usual
 
model.fit(x, y, epochs=1, shuffle=False)
32/32 [==============================] - 0s 1ms/step - loss: 0.2783 - mae: 0.4257
 
  

这里的loss是tensorflow库中实现了的损失函数，如果想自定义损失函数，然后将损失函数传入model.compile中，能正常按我们预想的work吗？

def custom_mse(y_true, y_pred):
    return tf.reduce_mean((y_true - y_pred)**2, axis=-1)
a_true = tf.constant([1., 1.5, 1.2])
a_pred = tf.constant([1., 2, 1.5])
custom_mse(a_true, a_pred)

tf.losses.MSE(a_true, a_pred)

以上结果证实了我们自定义loss的正确性，下面我们直接将自定义的loss置入compile中的loss参数中，看看会发生什么。

my_model = CustomModel(inputs, outputs)
my_model.compile(optimizer="adam", loss=custom_mse, metrics=["mae"])
my_model.fit(x, y, epochs=1, shuffle=False)
32/32 [==============================] - 0s 820us/step - loss: 0.1628 - mae: 0.3257
 

我们看到，这里的loss与我们与标准的tf.losses.MSE明显不同。这说明我们自定义的loss以这种方式直接传递进model.compile中，是完全错误的操作。

loss_tracker = keras.metrics.Mean(name="loss")
mae_metric = keras.metrics.MeanAbsoluteError(name="mae")
 
class MyCustomModel(keras.Model):
    tf.random.set_seed(100)
    def train_step(self, data):
        # Unpack the data. Its structure depends on your model and
        # on what you pass to `fit()`.
        x, y = data
 
        with tf.GradientTape() as tape:
            y_pred = self(x, training=True)  # Forward pass
            # Compute the loss value
            # (the loss function is configured in `compile()`)
            loss = custom_mse(y, y_pred)
            # loss += self.losses
 
        # Compute gradients
        trainable_vars = self.trainable_variables
        gradients = tape.gradient(loss, trainable_vars)
        # Update weights
        self.optimizer.apply_gradients(zip(gradients, trainable_vars))
         
        # Compute our own metrics
        loss_tracker.update_state(loss)
        mae_metric.update_state(y, y_pred)
        return {"loss": loss_tracker.result(), "mae": mae_metric.result()}
     
    @property
    def metrics(self):
        # We list our `Metric` objects here so that `reset_states()` can be
        # called automatically at the start of each epoch
        # or at the start of `evaluate()`.
        # If you don't implement this property, you have to call
        # `reset_states()` yourself at the time of your choosing.
        return [loss_tracker, mae_metric]
     
# Construct and compile an instance of CustomModel
inputs = keras.Input(shape=(32,))
outputs = keras.layers.Dense(1)(inputs)
my_model_beta = MyCustomModel(inputs, outputs)
my_model_beta.compile(optimizer="adam")
 
# Just use `fit` as usual
 
my_model_beta.fit(x, y, epochs=1, shuffle=False)
32/32 [==============================] - 0s 960us/step - loss: 0.2783 - mae: 0.4257
 

终于，通过跳过在 compile() 中传递损失函数，而在 train_step 中手动完成所有计算内容，我们获得了与之前默认tf.losses.MSE完全一致的输出，这才是我们想要的结果。

当我们在模型中想用自定义的损失函数，不能直接传入fit函数，而是需要在train_step中手动传入，完成计算过程。到此这篇关于tensorflow2 自定义损失函数使用的隐藏坑的文章就介绍到这了。

原文来自：https://www.jb51.net/article/218240.htm

本文地址：https://www.linuxprobe.com/tensorflow-linux-five.html编辑：向金平，审核员：逄增宝

Linux命令大全：https://www.linuxcool.com/

Linux系统大全：https://www.linuxdown.com/

红帽认证RHCE考试心得：https://www.rhce.net/