在Keras中使用Tensorflow Huber loss

def huber_loss(y_true, y_pred, delta=1.0):
    error = y_true - y_pred
    condition = tf.abs(error) < delta
    squared_loss = 0.5 * tf.square(error)
    linear_loss = delta * (tf.abs(error) - 0.5 * delta)
    return tf.where(condition, squared_loss, linear_loss)

import tensorflow as tf
from tensorflow.keras import layers, models

def huber_loss(y_true, y_pred, delta=1.0):
    error = y_true - y_pred
    condition = tf.abs(error) < delta
    squared_loss = 0.5 * tf.square(error)
    linear_loss = delta * (tf.abs(error) - 0.5 * delta)
    return tf.where(condition, squared_loss, linear_loss)

# 构建模型
model = models.Sequential()
model.add(layers.Dense(64, activation='relu', input_shape=(input_dim,)))
model.add(layers.Dense(1))

# 编译模型
model.compile(optimizer='adam', loss=huber_loss)

# 训练模型
model.fit(x_train, y_train, epochs=10, batch_size=32)