小编Zan*_*ang的帖子

我写了一个张量流CNN,它已经训练好了.我希望恢复它以便在几个样本上运行它但不幸的是它吐出来:

ValueError:没有要保存的变量

我的评估代码可以在这里找到:

import tensorflow as tf

import main
import Process
import Input

eval_dir = "/Users/Zanhuang/Desktop/NNP/model.ckpt-30"
checkpoint_dir = "/Users/Zanhuang/Desktop/NNP/checkpoint"

init_op = tf.initialize_all_variables()
saver = tf.train.Saver()

def evaluate():
  with tf.Graph().as_default() as g:
    sess.run(init_op)

    ckpt = tf.train.get_checkpoint_state(checkpoint_dir)

    saver.restore(sess, eval_dir)

    images, labels = Process.eval_inputs(eval_data = eval_data)

    forward_propgation_results = Process.forward_propagation(images)

    top_k_op = tf.nn.in_top_k(forward_propgation_results, labels, 1)

    print(top_k_op)

def main(argv=None):
    evaluate()

if __name__ == '__main__':
  tf.app.run()

我在tensorflow中构建了一个卷积神经网络.它经过培训,现在我打开包装并进行评估.

import main
import Process
import Input

eval_dir = "/Users/Zanhuang/Desktop/NNP/model.ckpt-250"
checkpoint_dir = "/Users/Zanhuang/Desktop/NNP/checkpoint"

def evaluate():
  with tf.Graph().as_default() as g:
    images, labels = Process.eval_inputs()
    forward_propgation_results = Process.forward_propagation(images)
    init_op = tf.initialize_all_variables()
    saver = tf.train.Saver()
    top_k_op = tf.nn.in_top_k(forward_propgation_results, labels, 1)

  with tf.Session(graph=g) as sess:
    tf.train.start_queue_runners(sess=sess)
    sess.run(init_op)
    saver.restore(sess, eval_dir)
    print(sess.run(top_k_op))


def main(argv=None):
    evaluate()

if __name__ == '__main__':
  tf.app.run()

不幸的是,出现了一个奇怪的错误,我不知道为什么.

W tensorflow/core/kernels/queue_base.cc:2
W tensorflow/core/kernels/queue_base.cc:294] _0_input_producer: Skipping cancelled enqueue attempt with queue not closed
W tensorflow/core/kernels/queue_base.cc:294] _1_batch/fifo_queue: Skipping cancelled enqueue attempt with queue not closed
E …

我一直在尝试将1750*1750图像输入Tensorflow,但在使用tf.image.decode_jpeg()函数将图像转换为Tensor之后,我不知道如何标记和提供数据.

目前,我的代码是:

import tensorflow as tf
import numpy as np

import imageflow
import os, glob

sess = tf.InteractiveSession()

def read_jpeg(filename_queue):
 reader = tf.WholeFileReader()
 key, value = reader.read(filename_queue)

 my_img = tf.image.decode_jpeg(value)
 my_img.set_shape([1750, 1750, 1])
 print(value)
 return my_img

#####################################################
def read_image_data():
 jpeg_files = []
 images_tensor = []

 i = 1
 WORKING_PATH = "/Users/Zanhuang/Desktop/NNP/DATA"
 jpeg_files_path = glob.glob(os.path.join(WORKING_PATH, '*.jpeg'))

 for filename in jpeg_files_path:
    print(i)
    i += 1
    jpeg_files.append(filename)


 filename_queue = tf.train.string_input_producer(jpeg_files)

 mlist = [read_jpeg(filename_queue) for _ in range(len(jpeg_files))]

 init = tf.initialize_all_variables()

 sess = tf.Session() …

我建立了一个卷积模型，只是发现我的代码或Tensorflow的代码中存在大量内存泄漏。谁能发现问题并深入了解问题所在？

以下是一个最小的可复制示例及其一些输出：

Process.py：

import os
import sys

import tensorflow as tf
import Input

import os, re

FLAGS = tf.app.flags.FLAGS
TOWER_NAME = 'tower'

tf.app.flags.DEFINE_integer('batch_size', 1, "hello")
tf.app.flags.DEFINE_string('data_dir', '/home/zan/Desktop/Neural-Network-Prostate', "hello")

NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = Input.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = Input.NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
NUM_EPOCHS_PER_DECAY = 3

MOVING_AVERAGE_DECAY = 0.9999
NUM_EPOCHS_PER_DECAY = 30
LEARNING_RATE_DECAY_FACTOR = 0.1
INITIAL_LEARNING_RATE = 0.1


def _activation_summary(x):
  tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name)
  tf.histogram_summary(tensor_name + '/activations', x)
  tf.scalar_summary(tensor_name + '/sparsity', tf.nn.zero_fraction(x))

def inputs():
  if not FLAGS.data_dir:
    raise ValueError('Source Data Missing')
  data_dir = FLAGS.data_dir
  images, labels …