TensorFlow 2中带导数的损失函数

Question

我使用TF2（2.3.0）NN来近似求解ODE:y'+3y=0的函数y

我已经定义了cutsom loss类和函数，在该类和函数中，我试图区分单个输出与单个输入，因此方程成立，前提是y_true为零：

from tensorflow.keras.losses import Loss
import tensorflow as tf

class CustomLossOde(Loss):
    def __init__(self, x, model, name='ode_loss'):
        super().__init__(name=name)
        self.x = x
        self.model = model

    def call(self, y_true, y_pred):

        with tf.GradientTape() as tape:
            tape.watch(self.x)
            y_p = self.model(self.x)


        dy_dx = tape.gradient(y_p, self.x)
        loss = tf.math.reduce_mean(tf.square(dy_dx + 3 * y_pred - y_true))
        return loss

但运行以下NN：

import tensorflow as tf
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense
from tensorflow.keras import Input
from custom_loss_ode import CustomLossOde


num_samples = 1024
x_train = 4 * (tf.random.uniform((num_samples, )) - 0.5)
y_train = tf.zeros((num_samples, ))
inputs = Input(shape=(1,))
x = Dense(16, 'tanh')(inputs)
x = Dense(8, 'tanh')(x)
x = Dense(4)(x)
y = Dense(1)(x)
model = Model(inputs=inputs, outputs=y)
loss = CustomLossOde(model.input, model)
model.compile(optimizer=Adam(learning_rate=0.01, beta_1=0.9, beta_2=0.99),loss=loss)
model.run_eagerly = True
model.fit(x_train, y_train, batch_size=16, epochs=30)

现在我从第一个时代得到了0的损失，这没有任何意义

我已经从函数中打印了y_true和y_test，它们看起来还可以，所以我怀疑问题出在我未能成功打印的渐变中。 通知任何帮助

Answer 1

在这种情况下，使用高级KerasAPI定义自定义损失有点困难。相反，我将从scracth编写训练循环，因为它允许对您所能做的事情进行更细粒度的控制

我从这两位导游那里得到了灵感：

• Advanced Automatic Differentiation
• Writing a training loop from scratch

基本上，我使用了多个磁带可以无缝交互的事实。我使用一个来计算损失函数，另一个来计算要由优化器传播的梯度

import tensorflow as tf
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense
from tensorflow.keras import Input

num_samples = 1024
x_train = 4 * (tf.random.uniform((num_samples, )) - 0.5)
y_train = tf.zeros((num_samples, ))
inputs = Input(shape=(1,))
x = Dense(16, 'tanh')(inputs)
x = Dense(8, 'tanh')(x)
x = Dense(4)(x)
y = Dense(1)(x)
model = Model(inputs=inputs, outputs=y)

# using the high level tf.data API for data handling
x_train = tf.reshape(x_train,(-1,1))
dataset = tf.data.Dataset.from_tensor_slices((x_train,y_train)).batch(1)

opt = Adam(learning_rate=0.01, beta_1=0.9, beta_2=0.99)
for step, (x,y_true) in enumerate(dataset):
    # we need to convert x to a variable if we want the tape to be 
    # able to compute the gradient according to x
    x_variable = tf.Variable(x) 
    with tf.GradientTape() as model_tape:
        with tf.GradientTape() as loss_tape:
            loss_tape.watch(x_variable)
            y_pred = model(x_variable)
        dy_dx = loss_tape.gradient(y_pred, x_variable)
        loss = tf.math.reduce_mean(tf.square(dy_dx + 3 * y_pred - y_true))
    grad = model_tape.gradient(loss, model.trainable_variables)
    opt.apply_gradients(zip(grad, model.trainable_variables))
    if step%20==0:
        print(f"Step {step}: loss={loss.numpy()}")