重复推理后模型推理运行时间增加

Question

我正在编写一个tensorflow项目，在该项目中我手动编辑每个权重和偏差，因此我使用字典设置权重和偏差，而不是使用tf.layers.dense，并让tensorflow负责更新权重。（这是我想出的最干净的方法，尽管可能不太理想）

我在每次迭代中为固定模型提供相同的数据，但是在整个程序执行过程中运行时间会增加。你知道吗

我删掉了代码中的几乎所有内容，这样我就可以看到问题所在，但我无法理解是什么导致了运行时间的增加。你知道吗

---Games took   2.6591222286224365 seconds ---
---Games took   3.290001153945923 seconds ---
---Games took   4.250034332275391 seconds ---
---Games took   5.190149307250977 seconds ---

编辑：我已经设法通过使用占位符来减少运行时间，占位符不向图中添加额外的节点，但是运行时间仍然以较慢的速度增加。我想删除这个运行时间增长。（一段时间后从0.1秒变为1秒以上）

这是我的全部密码：

import numpy as np
import tensorflow as tf
import time

n_inputs = 9
n_class = 9

n_hidden_1 = 20

population_size = 10
weights = []
biases = []
game_steps = 20 #so we can see performance loss faster

# 2 games per individual
games_in_generation = population_size/2


def generate_initial_population(my_population_size):
    my_weights = []
    my_biases = []

    for key in range(my_population_size):
        layer_weights = {
            'h1': tf.Variable(tf.truncated_normal([n_inputs, n_hidden_1], seed=key)),
            'out': tf.Variable(tf.truncated_normal([n_hidden_1, n_class], seed=key))
        }
        layer_biases = {
            'b1': tf.Variable(tf.truncated_normal([n_hidden_1], seed=key)),
            'out': tf.Variable(tf.truncated_normal([n_class], seed=key))
        }
        my_weights.append(layer_weights)
        my_biases.append(layer_biases)
    return my_weights, my_biases


weights, biases = generate_initial_population(population_size)
data = tf.placeholder(dtype=tf.float32) #will add shape later

def model(x):
    out_layer = tf.add(tf.matmul([biases[1]['b1']], weights[1]['out']),  biases[1]['out'])
    return out_layer


def play_game():


     model_input = [0] * 9
     model_out = model(data)

     for game_step in range(game_steps):

        move = sess.run(model_out, feed_dict={data: model_input})[0]


sess = tf.Session()
sess.run(tf.global_variables_initializer())
while True:
    start_time = time.time()
    for _ in range(int(games_in_generation)):
        play_game()
    print("---Games took   %s seconds ---" % (time.time() - start_time))

Answer 1

这段代码中有一些奇怪的地方，所以给你一个真正解决潜在问题的答案是很棘手的。但是，我可以解决您观察到的运行时间增长问题。下面，我修改了您的代码，以从游戏循环中提取输入模式生成和对model的调用。你知道吗

import numpy as np
import tensorflow as tf
import time

n_inputs = 9
n_class = 9

n_hidden_1 = 20

population_size = 10
weights = []
biases = []
game_steps = 20 #so we can see performance loss faster

# 2 games per individual
games_in_generation = population_size/2


def generate_initial_population(my_population_size):
    my_weights = []
    my_biases = []

    for key in range(my_population_size):
        layer_weights = {
            'h1': tf.Variable(tf.truncated_normal([n_inputs, n_hidden_1], seed=key)),
            'out': tf.Variable(tf.truncated_normal([n_hidden_1, n_class], seed=key))
        }
        layer_biases = {
            'b1': tf.Variable(tf.truncated_normal([n_hidden_1], seed=key)),
            'out': tf.Variable(tf.truncated_normal([n_class], seed=key))
        }
        my_weights.append(layer_weights)
        my_biases.append(layer_biases)
    return my_weights, my_biases


weights, biases = generate_initial_population(population_size)


def model(x):
    out_layer = tf.add(tf.matmul([biases[1]['b1']], weights[1]['out']),  biases[1]['out'])
    return out_layer


def play_game():

    # Extract input pattern generation.
    model_input = np.float32([[0]*9])
    model_out = model(model_input)

    for game_step in range(game_steps):

            start_time = time.time()
            move = sess.run(model_out)[0]

            # print(" -Step took   %s seconds  -" % (time.time() - start_time))


sess = tf.Session()
sess.run(tf.global_variables_initializer())
for _ in range(5):
    start_time = time.time()
    for _ in range(int(games_in_generation)):
        play_game()
    print(" -Games took   %s seconds  -" % (time.time() - start_time))

如果运行，此代码将提供如下信息：

 -Games took   0.42223644256591797 seconds  -
 -Games took   0.13168787956237793 seconds  -
 -Games took   0.2452383041381836 seconds  -
 -Games took   0.20023465156555176 seconds  -
 -Games took   0.19905781745910645 seconds  -

显然，这解决了您观察到的运行时间增长问题。它还将观察到的最大运行时间减少了一个数量级！发生这种情况的原因是，每次调用model时，实际上是在创建一堆^{}对象，并试图将这些对象添加到图中。这种误解很常见，是因为您试图在命令式python代码中使用张量，就好像它们是python变量一样。我建议在继续之前检查所有的graphs guide。你知道吗

还需要注意的是，在TensorFlow中，这不是将值传递给图形的正确方法。我可以看到，在游戏的每个迭代过程中，您都希望向模型传递不同的值，但是您不能通过向python函数传递值来实现这一点。必须在模型图中创建一个^{}，并将希望模型处理的值加载到该占位符上。有很多方法可以做到这一点，但是您可以找到一个例子here。我希望这对你有帮助！你知道吗