Tensorflow Structuring Model

codes
https://github.com/satyrswang/blog-jianshu/blob/master/Decorator.py

设计Model

• class Model需要

        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))

• def prediction(self)封装住

 if not self._prediction:
        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)

• def optimize(self)封装住

 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)

• def error(self)

@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

-__init__部分

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

• 使用Lazy Property 呢？

import functools
#这里将if not self._attributename:抽离，利用了[参数检查](http://www.jianshu.com/p/9eab7ab1a54a)，getattr相当于call Model中添加了 @lazy_property的func
def lazy_property(function):
    attribute = '_cache_' + function.__name__
    @property
    @functools.wraps(function)
    def decorator(self):
        if not hasattr(self, attribute):
            setattr(self, attribute, function(self))
        return getattr(self, attribute)
    return decorator

class Model:

    def __init__(self, data, target):
        self.data = data
        self.target = target
        self.prediction
        self.optimize
        self.error

    @lazy_property
    def prediction(self):
        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
        return tf.nn.softmax(incoming)

    @lazy_property
    def optimize(self):
        cross_entropy = -tf.reduce_sum(self.target, tf.log(self.prediction))
        optimizer = tf.train.RMSPropOptimizer(0.03)
        return optimizer.minimize(cross_entropy)

    @lazy_property
    def error(self):
        mistakes = tf.not_equal(
            tf.argmax(self.target, 1), tf.argmax(self.prediction, 1))
        return tf.reduce_mean(tf.cast(mistakes, tf.float32))

• 在__init__中定义了所有properties，当tf.initialize_variables()时，整个graph已经建立好了。

组织Graph

• 利用Decorator

import functools
#定义func的scope
def define_scope(function):
    attribute = '_cache_' + function.__name__

    @property
    @functools.wraps(function)
    def decorator(self):
        if not hasattr(self, attribute):
#这里是主要部分，将Model里的func作为一个scope，在这个scope中定义func
            with tf.variable_scope(function.__name):
                setattr(self, attribute, function(self))
        return getattr(self, attribute)

    return decorator

reference