时间：2022-08-08 08:21:04 | 栏目：Python代码 | 点击：次
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。
这里以tensorflow2官网中的例子来说明：
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
<tensorflow.python.keras.callbacks.History at 0x7ff7edf6dfd0>
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？
答案竟然是否定的，而且没有错误提示，只是loss计算不会符合我们的预期。
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.Tensor: shape=(), dtype=float32, numpy=0.11333332>
tf.losses.MSE(a_true, a_pred)
<tf.Tensor: shape=(), dtype=float32, numpy=0.11333332>
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 <tensorflow.python.keras.callbacks.History at 0x7ff7edeb7810>
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。
正确运用自定义loss的姿势是什么呢？下面揭晓。
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
<tensorflow.python.keras.callbacks.History at 0x7ff7eda3d810>
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。
总结一下，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。