Get Gradients with Keras Tensorflow 2.0

Question

I would like to keep track of the gradients over tensorboard. However, since session run statements are not a thing anymore and the write_grads argument of tf.keras.callbacks.TensorBoard is depricated, I would like to know how to keep track of gradients during training with Keras or tensorflow 2.0.

My current approach is to create a new callback class for this purpose, but without success. Maybe someone else knows how to accomplish this kind of advanced stuff.

The code created for testing is shown below, but runs into errors independently of printing a gradient value to console or tensorboard.

import tensorflow as tf
from tensorflow.python.keras import backend as K

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu', name='dense128'),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation='softmax', name='dense10')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])


class GradientCallback(tf.keras.callbacks.Callback):
    console = True

    def on_epoch_end(self, epoch, logs=None):
        weights = [w for w in self.model.trainable_weights if 'dense' in w.name and 'bias' in w.name]
        loss = self.model.total_loss
        optimizer = self.model.optimizer
        gradients = optimizer.get_gradients(loss, weights)
        for t in gradients:
            if self.console:
                print('Tensor: {}'.format(t.name))
                print('{}\n'.format(K.get_value(t)[:10]))
            else:
                tf.summary.histogram(t.name, data=t)


file_writer = tf.summary.create_file_writer("./metrics")
file_writer.set_as_default()

# write_grads has been removed
tensorboard_cb = tf.keras.callbacks.TensorBoard(histogram_freq=1, write_grads=True)
gradient_cb = GradientCallback()

model.fit(x_train, y_train, epochs=5, callbacks=[gradient_cb, tensorboard_cb])

• Priniting bias gradients to console (console parameter = True) leads to: AttributeError: 'Tensor' object has no attribute 'numpy'
• Writing to tensorboard (console parameter = False) creates: TypeError: Using a tf.Tensor as a Python bool is not allowed. Use if t is not None: instead of if t: to test if a tensor is defined, and use TensorFlow ops such as tf.cond to execute subgraphs conditioned on the value of a tensor.

Answer 1

To compute the gradients of the loss against the weights, use

with tf.GradientTape() as tape:
    loss = model(model.trainable_weights)

tape.gradient(loss, model.trainable_weights)

This is (arguably poorly) documented on GradientTape.

We do not need to tape.watch the variable because trainable parameters are watched by default.

As a function, it can be written as

def gradient(model, x):
    x_tensor = tf.convert_to_tensor(x, dtype=tf.float32)
    with tf.GradientTape() as t:
        t.watch(x_tensor)
        loss = model(x_tensor)
    return t.gradient(loss, x_tensor).numpy()

Answer 2

Also have a look here: https://github.com/tensorflow/tensorflow/issues/31542#issuecomment-630495970

richardwth wrote a child class of Tensorboard.

I adapted it as follows:

class ExtendedTensorBoard(tf.keras.callbacks.TensorBoard):
    def _log_gradients(self, epoch):
        writer = self._writers['train']

        with writer.as_default(), tf.GradientTape() as g:
            # here we use test data to calculate the gradients
            features, y_true = list(val_dataset.batch(100).take(1))[0]

            y_pred = self.model(features)  # forward-propagation
            loss = self.model.compiled_loss(y_true=y_true, y_pred=y_pred)  # calculate loss
            gradients = g.gradient(loss, self.model.trainable_weights)  # back-propagation

            # In eager mode, grads does not have name, so we get names from model.trainable_weights
            for weights, grads in zip(self.model.trainable_weights, gradients):
                tf.summary.histogram(
                    weights.name.replace(':', '_') + '_grads', data=grads, step=epoch)

        writer.flush()

    def on_epoch_end(self, epoch, logs=None):
        # This function overwrites the on_epoch_end in tf.keras.callbacks.TensorBoard
        # but we do need to run the original on_epoch_end, so here we use the super function.
        super(ExtendedTensorBoard, self).on_epoch_end(epoch, logs=logs)

        if self.histogram_freq and epoch % self.histogram_freq == 0:
            self._log_gradients(epoch)