Question

我正在尝试从一个自我保存的.tfrecords文件中读取内容，以便在网络中使用它。因此，为确保它能正确读取，我尝试显示存储的图片。

我主要关注以下教程 How to write into and read from a TFRecords file in TensorFlow，但对其进行了一些更改，以输入.tfrecords文件的路径，并且图像尺寸为16x16x3。

div.asciigun {
    position: absolute;
    top: 30vw;
    left: 74vw;
    z-index: 1;
    width: 30vw;
    height: 15vw;
}

据我所知，无法查看tfrecords文件来查看其内容，所以我想使用教程中的这段代码来查看存储的图片。

因此，要对其进行测试，我已经读取了第一张图像，并使用此图片的200倍创建了张量，并且label = 1。但是每次我尝试运行它时，

都会发生错误

def show_all_images(srcpath):

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

data_path = srcpath  # address to save the hdf5 file
with tf.Session() as sess:
    feature = {'train/image': tf.FixedLenFeature([], tf.string),
               'train/label': tf.FixedLenFeature([], tf.int64)}
    # Create a list of filenames and pass it to a queue
    filename_queue = tf.train.string_input_producer([data_path], num_epochs=1)
    # Define a reader and read the next record
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    # Decode the record read by the reader
    features = tf.parse_single_example(serialized_example, features=feature)
    # Convert the image data from string back to the numbers
    image = tf.decode_raw(features['train/image'], tf.float32)
    print(image.shape)


    # Cast label data into int32
    label = tf.cast(features['train/label'], tf.int32)
    # Reshape image data into the original shape
    image = tf.reshape(image, [16, 16, 3])
    print(image.shape)

    # Any preprocessing here ...
    tmpim = [image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image,
             image,image,image,image,image,image,image,image,image,image]
    tmplbl = [1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,
              1,1,1,1,1,1,1,1,1,1,1,1,1]

    # Creates batches by randomly shuffling tensors
    images, labels = tf.train.shuffle_batch([tmpim, tmplbl], batch_size=10, capacity=70, num_threads=1, min_after_dequeue=10, enqueue_many = True)
    print(images.shape)

    init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
    sess.run(init_op)
    # Create a coordinator and run all QueueRunner objects
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    #for batch_index in range(1):
    img, lbl = sess.run([images, labels])
    img = img.astype(np.uint8)
    for j in range(6):
        plt.subplot(2, 3, j+1)
        plt.imshow(img[j, ...])
        plt.title('cat' if lbl[j]==0 else 'dog')
    plt.show()
    # Stop the threads
    coord.request_stop()

    # Wait for threads to stop
    coord.join(threads)
    sess.close()

输出为：

    img, lbl = sess.run([images, labels])

我的主要名字开头：

show_all_images（'mypath'+'traindata.tfrecords'）

我已经尝试了TensorFlow random_shuffle_queue is closed and has insufficient elements和其他一些解决方案，但没有任何效果

任何帮助将不胜感激！

RandomShuffleQueue'_2_shuffle_batch / random_shuffle_queue'已关闭且元素不足（要求10，当前大小为0）

0 个答案: