我正在编码一个tensorflow项目，在该项目中，我正在手动编辑每个权重和偏差，因此我像使用字典一样在旧tensorflow中设置权重和偏差，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，尽管可能并不理想）
我在每次迭代中向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。
我从代码中删除了几乎所有内容，因此我可以看到问题出在哪里，但我不明白是什么导致运行时间增加。
---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一个占位符来减少运行时间，该占位符没有向图形添加其他节点，但是运行时间仍然以较低的速率增加。我想消除这种运行时间的增长。 （一段时间后，它从0.1秒变为超过1秒）
这是我的完整代码：
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))
答案 0 :(得分：1)
此代码中发生了一些奇怪的事情，因此要给您一个真正能够解决潜在问题的答案将非常棘手。但是，我可以解决您所观察到的运行时间的增长。下面，我修改了您的代码以提取输入模式生成并从游戏循环中调用model。
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，此代码应为您提供以下内容：
---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，这可以解决您观察到的运行时间增长。它还将最大观察到的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，您实际上是在创建一堆tf.Tensor对象，并试图将其添加到图形中。这种误解是常见的，并且是由于您试图在命令式python代码中使用Tensors造成的，就像它们是python变量一样。我建议在继续操作之前先检查所有graphs guide。
还必须注意，这不是将值传递到TensorFlow中的图形的正确方法。我可以看到您想在游戏的每次迭代期间将不同的值传递给模型，但是您无法通过将值传递给python函数来实现这一点。您必须在模型图中创建一个tf.placeholder，并将要模型处理的值加载到该占位符上。有很多方法可以执行此操作，但是您可以找到一个示例here。希望对您有所帮助！
答案 1 :(得分：1)
我要添加另一个答案，因为对问题的最新编辑产生了实质性的变化。您仍然可以看到运行时间有所增长，因为您在model中仍然多次呼叫sess。您只是降低了向图中添加节点的频率。您需要做的是为要构建的每个模型创建一个新会话，并在完成后关闭每个会话。为此，我已经修改了您的代码：
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
def model(x):
out_layer = tf.add(tf.matmul([biases[1]['b1']], weights[1]['out']), biases[1]['out'])
return out_layer
def play_game(sess):
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]
while True:
for _ in range(int(games_in_generation)):
# Reset the graph.
tf.reset_default_graph()
weights, biases = generate_initial_population(population_size)
data = tf.placeholder(dtype=tf.float32) #will add shape later
# Create session.
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
start_time = time.time()
play_game(sess)
print("---Games took %s seconds ---" % (time.time() - start_time))
sess.close()
我在这里所做的工作是将对play_game的调用包装在with范围内定义的会话中，并在对sess.close的调用之后以play_game退出该会话。我还重置了默认图形。我已经运行了数百次迭代，却没有看到运行时间的增加。