【发布时间】：2016-06-17 19:14:18
【问题描述】：
我正在尝试使用 Tensorflow 构建高斯 RBM 模型。但是程序会占用太多内存。
gaussian_rbm.py
import tensorflow as tf
import math
import input_data
import numpy as np
def sample_prob(probs):
return tf.nn.relu(
tf.sign(
probs - tf.random_uniform(tf.shape(probs))))
class RBM(object):
""" represents a sigmoidal rbm """
def __init__(self, name, input_size, output_size, gaussian_std_val=0.1):
with tf.name_scope("rbm_" + name):
self.weights = tf.Variable(
tf.truncated_normal([input_size, output_size],
stddev=1.0 / math.sqrt(float(input_size))), name="weights")
self.v_bias = tf.Variable(tf.zeros([input_size]), name="v_bias")
self.h_bias = tf.Variable(tf.zeros([output_size]), name="h_bias")
self.input = tf.placeholder("float", shape=[None, 784])
#Gaussian
def_a = 1/(np.sqrt(2)*gaussian_std_val)
def_a = tf.constant(def_a, dtype=tf.float32)
self.a = tf.Variable( tf.ones(shape=[input_size]) * def_a,
name="a")
def propup(self, visible):
""" P(h|v) """
return tf.nn.sigmoid(tf.matmul(visible, self.weights) + self.h_bias)
def propdown(self, hidden):
""" P(v|h) """
# return tf.nn.sigmoid(tf.matmul(hidden, tf.transpose(self.weights)) + self.v_bias)
return ( tf.matmul(hidden, tf.transpose(self.weights)) + self.v_bias ) / (2 * (self.a * self.a))
def sample_h_given_v(self, v_sample):
""" Generate a sample from the hidden layer """
return sample_prob(self.propup(v_sample))
def sample_v_given_h(self, h_sample):
""" Generate a sample from the visible layer """
return self.sample_gaussian(self.propdown(h_sample))
def gibbs_hvh(self, h0_sample):
""" A gibbs step starting from the hidden layer """
v_sample = self.sample_v_given_h(h0_sample)
h_sample = self.sample_h_given_v(v_sample)
return [v_sample, h_sample]
def gibbs_vhv(self, v0_sample):
""" A gibbs step starting from the visible layer """
h_sample = self.sample_h_given_v(v0_sample)
v_sample = self.sample_v_given_h(h_sample)
return [h_sample, v_sample]
def sample_gaussian(self, mean_field):
return tf.random_normal(shape=tf.shape(mean_field),
mean=mean_field,
stddev=1.0 / (np.sqrt(2) * self.a))
def cd1(self, learning_rate=0.1):
" One step of contrastive divergence, with Rao-Blackwellization "
h_start = self.sample_h_given_v(self.input)
v_end = self.sample_v_given_h(h_start)
h_end = self.sample_h_given_v(v_end)
w_positive_grad = tf.matmul(tf.transpose(self.input), h_start)
w_negative_grad = tf.matmul(tf.transpose(v_end), h_end)
update_w = self.weights + (learning_rate * (w_positive_grad - w_negative_grad) / tf.to_float(tf.shape(self.input)[0]))
update_vb = self.v_bias + (learning_rate * tf.reduce_mean(self.input - v_end, 0))
update_hb = self.h_bias + (learning_rate * tf.reduce_mean(h_start - h_end, 0))
return [update_w, update_vb, update_hb]
def cal_err(self):
err = self.input - self.gibbs_vhv(self.input)[1]
return tf.reduce_mean(err * err)
test_mnist.py
import tensorflow as tf
import input_data
from gaussian_RBM import RBM
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
rbm_modle = RBM(name="gaussian_rbm", input_size=784, output_size=1000)
sess = tf.Session()
init_op = tf.initialize_all_variables()
sess.run(init_op)
for i in range(100):
print "step: %s"%i
for start, end in zip(range(0, len(trX), 128), range(128, len(trX), 128)):
rbm_modle.weights, rbm_modle.v_bias, rbm_modle.h_bias = \
sess.run(rbm_modle.cd1(), feed_dict={rbm_modle.input : trX[start : end]})
if start % 1280 == 0:
print sess.run(rbm_modle.cal_err(), feed_dict={rbm_modle.input : teX})
输出是
运行 test_mnist.py 提取 MNIST_data/train-images-idx3-ubyte.gz 提取 MNIST_data/train-labels-idx1-ubyte.gz 提取 MNIST_data/t10k-images-idx3-ubyte.gz 提取 MNIST_data/t10k-labels-idx1-ubyte.gz 我 tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:900] 成功 从 SysFS 读取的 NUMA 节点具有负值 (-1)，但必须有 至少一个 NUMA 节点，所以返回 NUMA 节点零 I tensorflow/core/common_runtime/gpu/gpu_init.cc:102] 找到设备 0 具有属性：名称：GeForce GTX 560 主要：2 次要：1 memoryClockRate (GHz) 1.62 pciBusID 0000:01:00.0 总内存： 1018.69MiB 可用内存：916.73MiB I tensorflow/core/common_runtime/gpu/gpu_init.cc:126] DMA：0 I 张量流/核心/common_runtime/gpu/gpu_init.cc:136] 0：是我 tensorflow/core/common_runtime/gpu/gpu_device.cc:684] 忽略 gpu 设备（设备：0，名称：GeForce GTX 560，pci 总线 ID：0000:01:00.0） 具有 Cuda 计算能力 2.1。最低要求的 Cuda 能力 是 3.5。步数：0 0.0911714 0.0781856 0.0773076 0.0770751 0.0776582 0.0764748 0.0755164 0.0741131 0.0726497 0.0712237 0.0701839 0.0686315 0.0664856 0.0658309 0.0646239 0.0626652 0.0616178 0.0610061 0.0598332 0.0588843 0.0587477 0.0572056 0.0561556 0.0554848 被杀
有没有办法监控内存？ 有人可以帮我吗？
【问题讨论】：
标签： python tensorflow