Tensorflow 代码结构注意事项

https://danijar.com/structuring-your-tensorflow-models/

1. 避免重复定义

普通的tensorflow model肯能是这样实现的

class Model:

    def __init__(self, data, target):
        data_size = int(data.get_shape()[1])
        target_size = int(target.get_shape()[1])
        weight = tf.Variable(tf.truncated_normal([data_size, target_size]))
        bias = tf.Variable(tf.constant(0.1, shape=[target_size]))
        incoming = tf.matmul(data, weight) + bias
        self._prediction = tf.nn.softmax(incoming)
        cross_entropy = -tf.reduce_sum(target, tf.log(self._prediction))
        self._optimize = tf.train.RMSPropOptimizer(0.03).minimize(cross_entropy)
        mistakes = tf.not_equal(
            tf.argmax(target, 1), tf.argmax(self._prediction, 1))
        self._error = tf.reduce_mean(tf.cast(mistakes, tf.float32))

    @property
    def prediction(self):
        return self._prediction

    @property
    def optimize(self):
        return self._optimize

    @property
    def error(self):
        return self._error

Just splitting the code into functions doesn’t work, since every time the functions are called, the graph would be extended by new code. Therefore, we have to ensure that the operations are added to the graph only when the function is called for the first time. This is basically lazy-loading.

class Model:

    def __init__(self, data, target):
        self.data = data
        self.target = target
        self._prediction = None
        self._optimize = None
        self._error = None

    @property
    def prediction(self):
        if not self._prediction:
            data_size = int(self.data.get_shape()[1])
            target_size = int(self.target.get_shape()[1])
            weight = tf.Variable(tf.truncated_normal([data_size, target_size]))
            bias = tf.Variable(tf.constant(0.1, shape=[target_size]))
            incoming = tf.matmul(self.data, weight) + bias
            self._prediction = tf.nn.softmax(incoming)
        return self._prediction

    @property
    def optimize(self):
        if not self._optimize:
            cross_entropy = -tf.reduce_sum(self.target, tf.log(self.prediction))
            optimizer = tf.train.RMSPropOptimizer(0.03)
            self._optimize = optimizer.minimize(cross_entropy)
        return self._optimize

    @property
    def error(self):
        if not self._error:
            mistakes = tf.not_equal(
                tf.argmax(self.target, 1), tf.argmax(self.prediction, 1))
            self._error = tf.reduce_mean(tf.cast(mistakes, tf.float32))
        return self._error