我想将jpeg格式的图像批量读取用于图像识别。这些图像位于/Image_p/文件夹中，图像名称在label.csv文件中列出，名称形式如14634_right。

我的问题是如何修改我的代码以成功批量读取图像？更具体地说，我不知道是否应该编写一个for循环，以及应该在哪里实现它。

在原始代码中，我在tf.train.shuffle_batch()函数上得到了错误信息：

ValueError: All shapes must be fully defined: [TensorShape([Dimension(None), Dimension(None), Dimension(3)]), TensorShape([])]

我的原始代码如下：

# filepathcsv_filepath = r'C:\Users\Jeffy\OneDrive\Course\NMDA\retinaProject\label.csv'# image parameterpic_num = 100pic_height = 64pic_width = 64batch_size = 10# =============================================================================# import libraryimport tensorflow as tfimport numpy as np# =============================================================================# read csv datacsv = np.loadtxt(open(csv_filepath,"rb"), delimiter=",", dtype='str')pic_filename = ["" for x in range(pic_num)]for i in range(pic_num):    pic_filename[i] = eval(csv[i,0]).decode("utf-8") +'.jpeg'# read the data into batchfor i in range(pic_num):    # read and decode the image    image_contents = tf.read_file('Image_p/' + eval(csv[i,0]).decode("utf-8") +'.jpeg')    image = tf.image.decode_jpeg(image_contents, channels=3)    image = tf.to_float(image)    # Generate batch    batch = tf.train.shuffle_batch([image, float(eval(csv[i,1]))],                                    batch_size = batch_size,                                     num_threads = 1,                                    capacity = batch_size * 100,                                     min_after_dequeue = batch_size * 10)with tf.Session() as sess:        sess.run(tf.global_variables_initializer())    coord = tf.train.Coordinator()    threads = tf.train.start_queue_runners(coord=coord)    image_tensor = sess.run([batch])    print(batch)    coord.request_stop()    coord.join(threads)

此外，我还编写了一个新文件，可以成功读取单张图像（感谢martianwars的帮助）。我的测试代码如下：

import tensorflow as tf    # read and decode the imageimage_contents = tf.read_file('Image_p/11247_left.jpeg')image = tf.image.decode_jpeg(image_contents, channels=3)with tf.Session() as sess:       img = sess.run(image)    print(img)

回答：

image 的形状将是 (?, ?, 3)，因为它尚未被读取，但你在decode_jpeg()函数中指定了通道数。尝试打印这个，

with tf.Session() as sess:       img = sess.run(image)    print(img)