python - 无法在 tensorflow 中成功读取图像

Question

我想批量读取jpeg图像以进行图像识别。图像位于/Image_p/文件中，图像名称列于 label.csv 文件中，如 14634_right 所示。

我的问题是如何修复我的代码以成功将图像批量读取？ 更具体地说，我不知道是否应该写一个for循环以及在哪里实现它。

对于原始代码，我在 tf.train.shuffle_batch() 上收到错误消息功能:

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

我的原始代码:

# filepath
csv_filepath = r'C:\Users\Jeffy\OneDrive\Course\NMDA\retinaProject\label.csv'

# image parameter
pic_num = 100
pic_height = 64
pic_width = 64
batch_size = 10

# =============================================================================
# import library
import tensorflow as tf
import numpy as np

# =============================================================================
# read csv data
csv = 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 batch
for 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)

另外，我还编写了一个可以成功读取图像的新文件(感谢 martianwars 的帮助)。我的测试代码:

import tensorflow as tf    
# read and decode the image
image_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)

Answer 1

image 将具有 (?, ?, 3) 形状，因为它尚未被读取，但您已在 decode_jpeg() 中指定了 channel 函数。尝试打印这个，

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