Python tf.keras GradientTape：获取关于输入的梯度

Tensorflow版本：Tensorflow 2.1

我想得到关于输入的梯度，而不是关于可训练权重的梯度。我将示例从调整为

---

但是，这不起作用，因为grads=tape.gradient（loss_value，model.inputs）返回[None]。这是不是有意的行为？如果是，建议使用什么方法来获取输入的梯度？

要使其正常工作，需要添加两件事：

将图像转换为tf.变量

使用tape.watch观察相对于所需变量的梯度

image = tf.Variable(input)
for iteration in range(400):
    with tf.GradientTape() as tape:
        tape.watch(image)
        # Run the forward pass of the layer.
        # The operations that the layer applies
        # to its inputs are going to be recorded
        # on the GradientTape.
        prediction = model(image, training=False)  # Logits for this minibatch

        # Compute the loss value for this minibatch.
        loss_value = loss_fun(target, prediction)

    # Use the gradient tape to automatically retrieve
    # the gradients of the trainable variables with respect to the loss.
    grads = tape.gradient(loss_value, image)
    #print(grads)  # output: [None]
    # Run one step of gradient descent by updating
    # the value of the variables to minimize the loss.
    optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
    optimizer.apply_gradients(zip([grads], [image]))

    print('Iteration {}'.format(iteration))

image = tf.Variable(input)
for iteration in range(400):
    with tf.GradientTape() as tape:
        tape.watch(image)
        # Run the forward pass of the layer.
        # The operations that the layer applies
        # to its inputs are going to be recorded
        # on the GradientTape.
        prediction = model(image, training=False)  # Logits for this minibatch

        # Compute the loss value for this minibatch.
        loss_value = loss_fun(target, prediction)

    # Use the gradient tape to automatically retrieve
    # the gradients of the trainable variables with respect to the loss.
    grads = tape.gradient(loss_value, image)
    #print(grads)  # output: [None]
    # Run one step of gradient descent by updating
    # the value of the variables to minimize the loss.
    optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
    optimizer.apply_gradients(zip([grads], [image]))

    print('Iteration {}'.format(iteration))