使用 Keras Tensorflow 2.0 获取梯度

问题描述

我想跟踪张量板上的梯度.但是，由于会话运行语句不再是一回事，并且 tf.keras.callbacks.TensorBoard 的 write_grads 参数被弃用，我想了解如何在使用 Keras 或 tensorflow 2.0 进行训练期间跟踪梯度.

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.

我目前的方法是为此目的创建一个新的回调类，但没有成功.也许其他人知道如何完成这种高级的东西.

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.

为测试创建的代码如下所示，但会在与将梯度值打印到控制台或张量板无关的情况下遇到错误.

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('{}
'.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])

• 将偏差梯度打印到控制台(控制台参数 = True)导致:AttributeError: 'Tensor' object has no attribute 'numpy'
• 写入 tensorboard(控制台参数 = False)会创建:TypeError:不允许使用 tf.Tensor 作为 Python bool.使用 if t is not None: 而不是 if t: 来测试是否定义了张量，并使用 TensorFlow ops 例如 tf.cond 来执行以张量为条件的子图张量的值.
• 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.

推荐答案

要计算损失对权重的梯度，请使用

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)

GradientTape.

我们不需要tape.watch变量，因为默认情况下会监视可训练的参数.

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

作为函数，可以写成

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()

这篇关于使用 Keras Tensorflow 2.0 获取梯度的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，WP2