2016年6月的git问题（ https://github.com/tensorflow/tensorflow/issues/1727 ）表明存在以下问题：

当前，GPUDevice中的分配器属于ProcessState，它本质上是全局单例。使用GPU的第一个会话将其初始化，并在进程关闭时释放自身。

因此，唯一的解决方法是使用进程并在计算后将其关闭。

示例代码：

import tensorflow as tf
import multiprocessing
import numpy as np

def run_tensorflow():

    n_input = 10000
    n_classes = 1000

    # Create model
    def multilayer_perceptron(x, weight):
        # Hidden layer with RELU activation
        layer_1 = tf.matmul(x, weight)
        return layer_1

    # Store layers weight & bias
    weights = tf.Variable(tf.random_normal([n_input, n_classes]))


    x = tf.placeholder("float", [None, n_input])
    y = tf.placeholder("float", [None, n_classes])
    pred = multilayer_perceptron(x, weights)

    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)

    init = tf.global_variables_initializer()

    with tf.Session() as sess:
        sess.run(init)

        for i in range(100):
            batch_x = np.random.rand(10, 10000)
            batch_y = np.random.rand(10, 1000)
            sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})

    print "finished doing stuff with tensorflow!"


if __name__ == "__main__":

    # option 1: execute code with extra process
    p = multiprocessing.Process(target=run_tensorflow)
    p.start()
    p.join()

    # wait until user presses enter key
    raw_input()

    # option 2: just execute the function
    run_tensorflow()

    # wait until user presses enter key
    raw_input()

因此，如果您在创建的进程中调用函数run_tensorflow()并关闭该进程（选项1），则会释放内存。如果仅运行run_tensorflow() （选项2），则在函数调用后不会释放内存。

一旦不再需要张量（在.run调用终止之前），就释放由张量分配的GPU内存（返回到TensorFlow内存池）。销毁变量容器后，释放为变量分配的GPU内存。在DirectSession的情况下（即sess = tf.Session（“”）），是关闭会话或显式重置会话的时间（添加到62c159ff中 ）

我使用numba释放gpu，使用tensorflow我找不到效果方法。

import tensorflow as tf
from numba import cuda

a = tf.constant([1.0,2.0,3.0],shape=[3],name='a')
b = tf.constant([1.0,2.0,3.0],shape=[3],name='b')
with tf.device('/gpu:1'):
    c = a+b

TF_CONFIG = tf.ConfigProto(
gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.1),
  allow_soft_placement=True)

sess = tf.Session(config=TF_CONFIG)
sess.run(tf.global_variables_initializer())
i=1
while(i<1000):
        i=i+1
        print(sess.run(c))

sess.close() # if don't use numba,the gpu can't be released
cuda.select_device(1)
cuda.close()
with tf.device('/gpu:1'):
    c = a+b

TF_CONFIG = tf.ConfigProto(
gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.5),
  allow_soft_placement=True)

sess = tf.Session(config=TF_CONFIG)

sess.run(tf.global_variables_initializer())
while(1):
        print(sess.run(c))