我想用Tensorflow建立一个高斯RBM模型。但该程序将使用太多的内存。张量流记忆问题
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 /列车图像 - 的idx3-ubyte.gz 提取MNIST_data/train-labels-idx1-ubyte.gz提取 MNIST_data/t10k-images-idx3-ubyte.g ž提取 MNIST_data/T10K-标签-IDX1-ubyte.gz我 tensorflow/stream_executor/CUDA/cuda_gpu_executor.cc：从SYSFS读900]成功 NUMA节点具有负值（-1），但必须至少是 一个NUMA节点，所以返回NUMA节点零点 tensorflow/core/common_runtime/gpu/gpu_init.cc：102] Found device 0 with properties：name：GeForce GTX 560 major：2 minor：1 memory_lockRate（GHz）1.62 pciBusID 0000：01：00.0总内存： 1018.69MiB空闲内存：916.73MiB I tensorflow/core/common_runtime/gpu/gpu_init.cc：126] DMA：0 I tensorflow/core/common_runtime/gpu/gpu_init.cc：136] 0：YI 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） 与Cuda计算能力2.1。最低要求的Cuda能力为 。步骤：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死亡
有没有一些方法来监视内存？ 有人可以帮我吗？
感谢您的帮助。我正在尝试用cpu-only tensorflow来运行此代码。但是我的程序仍然会中途死亡。 – MilkKnight