python - OutOfRangeError : FIFOQueue 'batch/fifo_queue' in tf.train.batch -

i want solve problem. checked num_epochs=none of tf.train.slice_input_producer , reduced batch_size 64 16. however, outofrangeerror not disappear. tried everything(on stackoverflow 'outofrange, fifoqueie, insufficient elements, train.batch, slice_input_producer'... if know solving problem, please let me know.

import matplotlib.pyplot plt import tensorflow tf import numpy np import os import time import re datetime import datetime  datetime import timedelta nets import pam_cnn, fd_cnn import load_jpeg_with_tensorflow  flags = tf.app.flags flags = flags.flags flags.height = 250 flags.width = 250 flags.num_classes = 2 flags.batch_size = 16  ######################################################## load data ######################################################## main_dir = './data/lfwdata/lfw_train/' log_dir = 'tmp/pam/'  num_classes = 2 # number of bubbles x 2  # batch_img, batch_label = load_jpeg_with_tensorflow.read_data_batch(train_dir, 'trainimagelist.csv', height, width, #                                                                    num_channels, batch_size=batch_size)  ######################################################## placeholder variable ########################################################  x = tf.placeholder(tf.float32, shape=[none, flags.height, flags.width, 3], name='input') y = tf.placeholder(tf.float32, shape=[none, num_classes], name='label') y_cls = tf.argmax(y, dimension=1)  image_batch, label_batch, file_batch = load_jpeg_with_tensorflow.read_data_batch(main_dir+'trainimagelist.csv', flags.height, flags.width, flags.batch_size)  ######################################################## training process ########################################################  keep_prob = tf.placeholder(tf.float32) prediction = fd_cnn.build_model(x, keep_prob) loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y)) tf.summary.scalar('loss', loss)  optimizer = tf.train.adamoptimizer(learning_rate=1e-3).minimize(loss)  validate_image_batch, validate_label_batch, validate_file_batch = load_jpeg_with_tensorflow.read_data_batch(main_dir+'testimagelist.csv', flags.height, flags.width, flags.batch_size) label_max = tf.argmax(y, 1) pre_max = tf.argmax(prediction, 1) correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) tf.summary.scalar('accuracy', accuracy)  starttime = datetime.now() iteration = 20  summary = tf.summary.merge_all() ######################################################## tensorflow run ######################################################## tf.session(config=tf.configproto(allow_soft_placement=true, log_device_placement=true)) sess:     saver = tf.train.saver()     summary_writer = tf.summary.filewriter(log_dir, sess.graph)      coord = tf.train.coordinator()     threads = tf.train.start_queue_runners(sess=sess, coord=coord)     sess.run(tf.initialize_all_variables())      in range(iteration):         images_, labels_ = sess.run([image_batch, label_batch])         # images_ = image_batch         # labels_ = label_batch         sess.run(optimizer, feed_dict={x : images_, y : labels_, keep_prob:0.5})          if % 10 == 0:             = datetime.now() - starttime             print('## time:', now, ' steps:', i)              rt = sess.run([label_max, pre_max, loss, accuracy], feed_dict={x : images_,                                                                            y : labels_,                                                                            keep_prob : 1.0})             print('prediction loss:', rt[2], ' accuracy:', rt[3])             # validation steps             validate_images_, validate_labels_ = sess.run([validate_image_batch, validate_label_batch])             rv = sess.run([label_max, pre_max, loss, accuracy], feed_dict={x: validate_images_,                                                                            y: validate_labels_,                                                                            keep_prob: 1.0})             print('validation loss:', rv[2], ' accuracy:', rv[3])             if (rv[3] > 0.9):                 break             # validation accuracy             summary_str = sess.run(summary, feed_dict={x: validate_images_,                                                        y: validate_labels_,                                                        keep_prob: 1.0})             summary_writer.add_summary(summary_str, i)             summary_writer.flush()          saver.save(sess, 'face_recog')  # save session     coord.request_stop()     coord.join(threads)     print('finish') 

'load_jpeg_with_tensorflow.py' below.

def get_input_queue(csv_file_name, num_epochs=none):     train_images = []     train_labels = []     line in open(csv_file_name, 'r'):         cols = re.split(',|\n', line)         train_images.append(cols[0])                                         train_labels.append([float(cols[1])])         # train_labels.append([float(cols[1]), float(cols[2])])     print([train_images, train_labels])     print("number of images :", len(train_images))     input_queue = tf.train.slice_input_producer([train_images, train_labels], num_epochs=num_epochs)         # should small num_epoch                                                                                                                             # batch_size x     return input_queue  def read_data(input_queue):     image_file = input_queue[0]     label = input_queue[1]      image = tf.image.decode_jpeg(tf.read_file(image_file), channels=3)      return image, label, image_file  def read_data_batch(csv_file_name, height, width, batch_size):     input_queue = get_input_queue(csv_file_name)     image, label, file_name = read_data(input_queue)     image = tf.reshape(image, [height, width, 3])      batch_image, batch_label, batch_file = tf.train.batch([image, label, file_name], batch_size=batch_size)                 # add allow_smaller_final_batch=true     batch_file = tf.reshape(batch_file, [batch_size,1])      return batch_image, batch_label, batch_file