Tensorflow: How to replace or modify gradient?

I would like to replace or modify the gradient of an op or portion of the graph in tensorflow. It would be ideal if I can use the existing gradient in the calculation.

In some ways this is the opposite to what tf.stop_gradient() does: instead of adding a calculation which is ignored when calculating gradients, I want a calculation which is only used when calculating gradients.

A simple example would be something which simply scales gradients by multiplying them with a constant (but does not multiply the forward calculation by a constant). Another example would be something which clips the gradients to a given range.

For TensorFlow 1.7 and TensorFlow 2.0 look at edit blow.

First define your custom gradient:

    def _const_mul_grad(unused_op, grad):
      return 5.0 * grad

Since you want nothing to happen in the forward pass, override the gradient of an identity operation with your new gradient:

    g = tf.get_default_graph()
    with g.gradient_override_map({"Identity": "CustomGrad"}):
      output = tf.identity(input, name="Identity")

Here is a working example with a layer that clips gradients in the backwards pass and does nothing in the forwards pass, using the same method:

    import tensorflow as tf

    def _clip_grad(unused_op, grad):
      return tf.clip_by_value(grad, -0.1, 0.1)

    input = tf.Variable([3.0], dtype=tf.float32)

    g = tf.get_default_graph()
    with g.gradient_override_map({"Identity": "CustomClipGrad"}):
      output_clip = tf.identity(input, name="Identity")
    grad_clip = tf.gradients(output_clip, input)

    # output without gradient clipping in the backwards pass for comparison:
    output = tf.identity(input)
    grad = tf.gradients(output, input)

    with tf.Session() as sess:
      print("with clipping:", sess.run(grad_clip)[0])
      print("without clipping:", sess.run(grad)[0])

Edit for TensorFlow 1.7 and TensorFlow 2.0

Since 1.7 there is a new way to redefine the gradient with shorter syntax, which also works with Tensorflow 2.0. It also allows to redefine the gradient of multiple operations at the same time. Here are the examples from above, rewritten for TensorFlow 1.7 and TensorFlow 2.0:

Layer that scales gradients in the backward pass:

    def scale_grad_layer(x):
      def grad(dy):
        return 5.0 * dy
      return tf.identity(x), grad

Example with a layer that clips gradients in the backward pass:

    def clip_grad_layer(x):
      def grad(dy):
        return tf.clip_by_value(dy, -0.1, 0.1)
      return tf.identity(x), grad

From: stackoverflow.com/q/43839431