tf.keras GradientTape：获取相对于输入的梯度

Question

Tensorflow 版本：Tensorflow 2.1

我想获得相对于输入的梯度，而不是相对于可训练权重的梯度。我将示例从https://www.tensorflow.org/guide/keras/train_and_evaluate 调整为

import tensorflow as tf
import numpy as np

physical_devices = tf.config.experimental.list_physical_devices('GPU')
assert len(physical_devices) > 0, 'Not enough GPU hardware devices available'
tf.config.experimental.set_memory_growth(physical_devices[0], True)

def loss_fun(y_true, y_pred):
    loss = tf.reduce_mean(tf.square(y_true - y_pred), axis=-1)
    return loss

# Create a dataset
x = np.random.rand(10, 180, 320, 3).astype(np.float32)
y = np.random.rand(10, 1).astype(np.float32)
dataset = tf.data.Dataset.from_tensor_slices((x, y)).batch(1)

# Create a model
base_model = tf.keras.applications.MobileNet(input_shape=(180, 320, 3), weights=None, include_top=False)
x = tf.keras.layers.GlobalAveragePooling2D()(base_model.output)
output = tf.keras.layers.Dense(1)(x)
model = tf.keras.models.Model(inputs=base_model.input, outputs=output)

for input, target in dataset:

    for iteration in range(400):
        with tf.GradientTape() as tape:
            # 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(input, 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, model.inputs)
        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, model.inputs))

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

但是，这不起作用，因为 grads = tape.gradient(loss_value, model.inputs) 返回 [None]。这是预期的行为吗？如果是，推荐的获取输入梯度的方法是什么？

Answer 1

要让它工作，需要添加两件事：

1. 将图像转换为 tf.Variable

2. 使用 tape.watch 观察所需变量的梯度

   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))