Question

我正在使用Tensorflow编写一个NN模型来近似正弦函数，我想使用二阶导数w.r.t.到我模型的损失函数中的输入。

我的代码还没有包含导数，但是我只是在我的损失函数中添加了输入张量（作为第一步），并使用了this作为第一种方法。

我的代码当前看起来像这样

import tensorflow as tf
import numpy as np

from tensorflow import keras
from numpy import random

# --- Settings
x_min = 0
x_max = 2*np.pi

n_train = 64
n_test = 64

# --- Generate dataset
x_train = random.uniform(x_min, x_max, n_train)
y_train = np.sin(x_train)

x_test = random.uniform(x_min, x_max, n_test)
y_test = np.sin(x_test)

# --- Create model
model = keras.Sequential()

model.add(keras.layers.Dense(64, activation="tanh", input_dim=1))
model.add(keras.layers.Dense(64, activation="tanh"))

model.add(keras.layers.Dense(1, activation="tanh"))

def custom_loss_wrapper(input_tensor):

    def custom_loss(y_true, y_pred):
        return keras.losses.mean_squared_error(y_true, y_pred) + keras.backend.mean(input_tensor)

    return custom_loss

# --- Configure learning process
model.compile(
        optimizer=keras.optimizers.Adam(0.01),
        loss=custom_loss_wrapper(model.input),
        metrics=['MeanSquaredError'])

# --- Train from dataset
model.fit(x_train, y_train, epochs=5, batch_size=32, validation_data=(x_test, y_test))

model.evaluate(x_test, y_test)

我的自定义损失函数只是计算均方误差并添加输入值。这应该没问题，但是我收到了错误

TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
  @tf.function
  def has_init_scope():
    my_constant = tf.constant(1.)
    with tf.init_scope():
      added = my_constant * 2
The graph tensor has name: dense_input:0

有人知道为什么会这样吗？

Answer 1

由于默认情况下TensorFlow 2.0及更高版本在急切模式下运行， Tensorflow op将检查输入的类型是否为 “ tensorflow.python.framework.ops.EagerTensor” ，并且由于已实现Keras，急切模式的输入将为“ tensorflow.python.framework.ops.Tensor” ，这将引发错误

class CustomScrollView: UIScrollView {

    private var oldContentSize: CGSize = .zero

    override var contentOffset: CGPoint {

        set {
            if oldContentSize == contentSize {
                super.contentOffset = newValue
            } else {
                super.contentOffset = super.contentOffset
                oldContentSize = contentSize
            }
        }

        get {
            return super.contentOffset
        }
    }
}

您可以通过明确告诉TensorFlow在Keras的急切模式下运行来将输入类型更改为EagerTensor。将此设置为true将解决问题

TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
  @tf.function
  def has_init_scope():
    my_constant = tf.constant(1.)
    with tf.init_scope():
      added = my_constant * 2

Tensorflow：自定义损失函数导致op在函数构建代码错误之外

1 个答案: