Expected size[1] in [0, 50], but got 100

pythonで画像認識プログラムを作っています。

メインの機能を実装中にエラーメッセージが発生しました。

エラーメッセージ

raceback (most recent call last):
File "C:\Users\S\AppData\Local\atom\app-1.22.0\new\mm\mcz_main.py", line 114, in <module>
main(ckpt)
File "C:\Users\S\AppData\Local\atom\app-1.22.0\new\mm\mcz_main.py", line 72, in main
coord.join(threads)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected size[1] in [0, 50], but got 100
[[Node: Slice = Slice[Index=DT_INT32, T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](control_dependency_1, stack, stack_1)]]

該当のソースコード

import sys
import cv2
import numpy as np
import tensorflow as tf
import tensorflow.python.platform
from datetime import datetime
import random
import time
import os

import mcz_input
import mcz_model

LOGDIR = r"C:\Users\S\AppData\Local\atom\app-1.22.0\new\mm\tmp\data%s" % datetime.now().isoformat()
print (LOGDIR)

flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_string('train', r"C:\Users\S\AppData\Local\atom\app-1.22.0\new\mm\train.txt", 'File name of train data')
flags.DEFINE_string('test', r"C:\Users\S\AppData\Local\atom\app-1.22.0\new\mm\test.txt", 'File name of train data')
flags.DEFINE_string('train_dir', LOGDIR , 'Directory to put the training data.')
flags.DEFINE_integer('max_steps', 100000, 'Number of steps to run trainer.')
flags.DEFINE_integer('batch_size', 120, 'Batch size Must divide evenly into the dataset sizes.')
flags.DEFINE_float('learning_rate', 1e-4, 'Initial learning rate.')

def main(ckpt = None):
with tf.Graph().as_default():
keep_prob = tf.placeholder("float")

    images, labels, _ = mcz_input.load_data([FLAGS.train], FLAGS.batch_size, shuffle = True, distored = True)
    logits = mcz_model.inference_deep(images, keep_prob, mcz_input.DST_INPUT_SIZE, mcz_input.NUM_CLASS)
    loss_value = mcz_model.loss(logits, labels)
    train_op = mcz_model.training(loss_value, FLAGS.learning_rate)
    acc = mcz_model.accuracy(logits, labels)


    saver = tf.train.Saver(max_to_keep = 0)
    sess = tf.Session()

    sess.run(tf.global_variables_initializer())
    if ckpt:
        print ('restore ckpt', ckpt)

        saver.restore(sess, ckpt)



    coord =tf.train.Coordinator()

    threads=tf.train.start_queue_runners(sess=sess, coord=coord)

    try:
        while not coord.should_stop():
           sess.run(train_op)

    except tf.errors.OutOfRangeError:
        print('Done training -- epoch limit reached')
    finally:
        coord.request_stop()
    coord.join(threads)
    sess.close()

    summary_op = tf.summary.merge_all()
    summary_writer = tf.summary.FileWriter(FLAGS.train_dir, sess.graph_def)

    for step in range(FLAGS.max_steps):
        start_time = time.time()
        _, loss_result, acc_res = sess.run([train_op, loss_value, acc], feed_dict={keep_prob: 0.99})

        duration = time.time() - start_time

        if step % 10 == 0:
            num_examples_per_step = FLAGS.batch_size
            examples_per_sec = num_examples_per_step / duration
            sec_per_batch = float(duration)

            format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f sec/batch)')
            print (format_str % (datetime.now(), step, loss_result, examples_per_sec, sec_per_batch))
            print ('acc_res', acc_res)

        if step % 100 == 0:
            summary_str = sess.run(summary_op,feed_dict={keep_prob: 1.0})
            summary_writer.add_summary(summary_str, step)

        if step % 1000 == 0 or (step + 1) == FLAGS.max_steps or loss_result == 0:
            checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
            saver.save(sess, checkpoint_path, global_step=step)

        if loss_result == 0:
            print('loss is zero')
            break