代码之家 › 专栏 › 技术社区 › sdr2002

张量流的RNN慢化现象

lstm slice tensorflow

sdr2002 · 技术社区 · 7 年前

我不知道它是否真的有,所以我把这个帖子留在了so。下面是此问题的玩具代码:

import tensorflow as tf
import numpy as np
import time

def network(input_list):
    input,init_hidden_c,init_hidden_m = input_list
    cell = tf.nn.rnn_cell.BasicLSTMCell(256, state_is_tuple=True)
    init_hidden = tf.nn.rnn_cell.LSTMStateTuple(init_hidden_c, init_hidden_m)
    states, hidden_cm = tf.nn.dynamic_rnn(cell, input, dtype=tf.float32, initial_state=init_hidden)
    net = [v for v in tf.trainable_variables()]
    return states, hidden_cm, net

def action(x, h_c, h_m):
    t0 = time.time()
    outputs, output_h = sess.run([rnn_states[:,-1:,:], rnn_hidden_cm], feed_dict={
        rnn_input:x,
        rnn_init_hidden_c: h_c,
        rnn_init_hidden_m: h_m
    })
    dt = time.time() - t0
    return outputs, output_h, dt

rnn_input = tf.placeholder("float", [None, None, 512])
rnn_init_hidden_c = tf.placeholder("float", [None,256])
rnn_init_hidden_m = tf.placeholder("float", [None,256])
rnn_input_list = [rnn_input, rnn_init_hidden_c, rnn_init_hidden_m]
rnn_states, rnn_hidden_cm, rnn_net = network(rnn_input_list)

feed_input = np.random.uniform(low=-1.,high=1.,size=(1,1,512))
feed_init_hidden_c = np.zeros(shape=(1,256))
feed_init_hidden_m = np.zeros(shape=(1,256))

sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(10000):
    _, output_hidden_cm, deltat = action(feed_input, feed_init_hidden_c, feed_init_hidden_m)
    if i % 10 == 0:
        print 'Running time: ' + str(deltat)
    (feed_init_hidden_c, feed_init_hidden_m) = output_hidden_cm
    feed_input = np.random.uniform(low=-1.,high=1.,size=(1,1,512))

[不重要]此代码的作用是从包含LSTM的“network()”函数生成输出,其中输入的时间维度为1,因此输出也为1,并拉入&运行每个步骤的初始状态。

我不知道为什么[:,-1:,:]运行时会出现时间的指数增长。这是不是tensorflow的性质还没有被记录,但速度特别慢(可能会自己添加更多图形?)? 谢谢你,希望这篇文章不会给其他用户带来这样的错误。

2 回复 | 直到 7 年前

Björn Mattsson 6 年前

我遇到了同样的问题,每次运行TensorFlow时,TensorFlow都会变慢,在调试时发现了这个问题。以下是我的情况的简短描述,以及我是如何解决的,以供将来参考。希望它能为人们指明正确的方向,为他们节省一些时间。

就我而言,问题主要是我没有利用 feed_dict 在执行时提供网络状态 sess.run() .相反,我重新申报了 outputs , final_state 和 prediction https://github.com/tensorflow/tensorflow/issues/1439#issuecomment-194405649

# defining the network
lstm_layer = rnn.BasicLSTMCell(num_units, forget_bias=1)
outputs, final_state = rnn.static_rnn(lstm_layer, input, initial_state=rnn_state, dtype='float32')
prediction = tf.nn.softmax(tf.matmul(outputs[-1], out_weights)+out_bias)

for input_data in data_seq:
    # redeclaring, stupid stupid...
    outputs, final_state = rnn.static_rnn(lstm_layer, input, initial_state=rnn_state, dtype='float32')
    prediction = tf.nn.softmax(tf.matmul(outputs[-1], out_weights)+out_bias)
    p, rnn_state = sess.run((prediction, final_state), feed_dict={x: input_data})

当然,解决方案是在开始时只声明一次节点,并为新数据提供。代码从半慢(开始时>15毫秒)到每次迭代都变慢,到在大约1毫秒内执行每次迭代。我的新代码如下所示:

out_weights = tf.Variable(tf.random_normal([num_units, n_classes]), name="out_weights")
out_bias = tf.Variable(tf.random_normal([n_classes]), name="out_bias")

# placeholder for the network state
state_placeholder = tf.placeholder(tf.float32, [2, 1, num_units])
rnn_state = tf.nn.rnn_cell.LSTMStateTuple(state_placeholder[0], state_placeholder[1])

x = tf.placeholder('float', [None, 1, n_input])
input = tf.unstack(x, 1, 1)

# defining the network
lstm_layer = rnn.BasicLSTMCell(num_units, forget_bias=1)
outputs, final_state = rnn.static_rnn(lstm_layer, input, initial_state=rnn_state, dtype='float32')

prediction = tf.nn.softmax(tf.matmul(outputs[-1], out_weights)+out_bias)

# actual network state, which we input with feed_dict
_rnn_state = tf.nn.rnn_cell.LSTMStateTuple(np.zeros((1, num_units), dtype='float32'), np.zeros((1, num_units), dtype='float32'))

it = 0
for input_data in data_seq:
    encl_input = [[input_data]]
    p, _rnn_state = sess.run((prediction, final_state), feed_dict={x: encl_input, rnn_state: _rnn_state})
    print("{} - {}".format(it, p))
    it += 1

将声明从for循环中移出也解决了sdrop 2002的问题,即执行切片 outputs[-1] sess.run() 在for循环内。

sdr2002 7 年前

def action(x, h_c, h_m):
    t0 = time.time()
    outputs, output_h = sess.run([rnn_states, rnn_hidden_cm], feed_dict={
        rnn_input:x,
        rnn_init_hidden_c: h_c,
        rnn_init_hidden_m: h_m
    })
    outputs = outputs[:,-1:,:]
    dt = time.time() - t0
    return outputs, output_h, dt