python - 量化 Keras 神经网络模型

Question

最近，我开始使用 Tensorflow + Keras 创建神经网络，我想尝试 Tensorflow 中提供的量化功能。到目前为止，使用 TF 教程中的示例进行试验效果很好，我有这个基本的工作示例(来自 https://www.tensorflow.org/tutorials/keras/basic_classification):

import tensorflow as tf
from tensorflow import keras

fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

# fashion mnist data labels (indexes related to their respective labelling in the data set)
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

# preprocess the train and test images
train_images = train_images / 255.0
test_images = test_images / 255.0

# settings variables
input_shape = (train_images.shape[1], train_images.shape[2])

# create the model layers
model = keras.Sequential([
keras.layers.Flatten(input_shape=input_shape),
keras.layers.Dense(128, activation=tf.nn.relu),
keras.layers.Dense(10, activation=tf.nn.softmax)
])

# compile the model with added settings
model.compile(optimizer=tf.train.AdamOptimizer(),
          loss='sparse_categorical_crossentropy',
          metrics=['accuracy'])

# train the model
epochs = 3
model.fit(train_images, train_labels, epochs=epochs)

# evaluate the accuracy of model on test data
test_loss, test_acc = model.evaluate(test_images, test_labels)
print('Test accuracy:', test_acc)

现在，我想在学习和分类过程中使用量化。量化文档(https://www.tensorflow.org/performance/quantization)(该页面自 cca 2018 年 9 月 15 日起不再可用)建议使用这段代码:

loss = tf.losses.get_total_loss()
tf.contrib.quantize.create_training_graph(quant_delay=2000000)
optimizer = tf.train.GradientDescentOptimizer(0.00001)
optimizer.minimize(loss)

但是，它不包含有关此代码应在何处使用或应如何将其连接到 TF 代码的任何信息(甚至没有提及使用 Keras 创建的高级模型)。我不知道这个量化部分与之前创建的神经网络模型有何关系。仅在神经网络代码之后插入它会遇到以下错误:

Traceback (most recent call last):
  File "so.py", line 41, in <module>
    loss = tf.losses.get_total_loss()
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/losses/util.py", line 112, in get_total_loss
    return math_ops.add_n(losses, name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/math_ops.py", line 2119, in add_n
    raise ValueError("inputs must be a list of at least one Tensor with the "
ValueError: inputs must be a list of at least one Tensor with the same dtype and shape

是否可以通过这种方式量化 Keras NN 模型，或者我是否遗漏了一些基本的东西？我想到的一个可能的解决方案是使用低级 TF API 而不是 Keras(需要做大量工作来构建模型)，或者可能尝试从 Keras 模型中提取一些较低级的方法。

Answer 1

在其他答案中提到，TensorFlow Lite 可以帮助您进行网络量化。

TensorFlow Lite provides several levels of support for quantization.

Tensorflow Lite post-training quantization quantizes weights and activations post training easily. Quantization-aware training allows for training of networks that can be quantized with minimal accuracy drop; this is only available for a subset of convolutional neural network architectures.

所以首先，你需要决定是否需要post-training quantization或 quantization-aware training .例如，如果您已经将模型保存为 *.h5 文件，您可能希望按照@Mitiku 的说明进行训练后量化。

如果您希望通过模拟量化在训练中的效果(使用您在问题中引用的方法)来获得更高的性能，并且您的模型在量化支持的 CNN 架构子集中-意识培训，this example可能在 Keras 和 TensorFlow 之间的交互方面对您有所帮助。基本上，您只需在模型定义及其拟合之间添加以下代码:

sess = tf.keras.backend.get_session()
tf.contrib.quantize.create_training_graph(sess.graph)
sess.run(tf.global_variables_initializer())