Question

我正在尝试运行“猫和狗”示例，但我陷入了输入数据步骤。有人可以帮助我理解为什么我做错了并帮助我解决它吗？

先谢谢了。 ps：我不太清楚为什么会在C：\ Users \ siqiz \ Desktop \ tensorflowLearing \ 01Catsvsdogs \ traincat.2893.jpg中出现错误，因为我的所有图片都应保存为C：\ Users \ siqiz \ Desktop \ tensorflowLearing \ 01Catsvsdogs \ train \ cat.0.jpg

import matplotlib.pyplot as plt

BATCH_SIZE = 2
CAPACITY = 256
IMG_W = 208
IMG_H = 208

train_dir = 'C:\\Users\\siqiz\\Desktop\\tensorflowLearing\\01Catsvsdogs\\train\\'

image_list, label_list = get_files(train_dir)
image_batch, label_batch = get_batch(image_list, label_list, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)

with tf.Session() as sess:
    i = 0
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)

    try:
        while not coord.should_stop() and i<1:

            img, label = sess.run([image_batch, label_batch])

            # just test one batch
            for j in np.arange(BATCH_SIZE):
                print('label: %d' %label[j])
                plt.imshow(img[j,:,:,:])
                plt.show()
            i+=1

    except tf.errors.OutOfRangeError:
        print('done!')
    finally:
        coord.request_stop()
    coord.join(threads)


def get_batch(image, label, image_W, image_H, batch_size, capacity):
    '''
    Args:
        image: list type
        label: list type
        image_W: image width
        image_H: image height
        batch_size: batch size
        capacity: the maximum elements in queue
    Returns:
        image_batch: 4D tensor [batch_size, width, height, 3], dtype=tf.float32
        label_batch: 1D tensor [batch_size], dtype=tf.int32
    '''

    image = tf.cast(image, tf.string)
    label = tf.cast(label, tf.int32)

    # make an input queue
    input_queue = tf.train.slice_input_producer([image, label])

    label = input_queue[1]
    image_contents = tf.read_file(input_queue[0])
    image = tf.image.decode_jpeg(image_contents, channels=3)

    ######################################
    # data argumentation should go to here
    ######################################

    image = tf.image.resize_image_with_crop_or_pad(image, image_W, image_H)


    image = tf.image.per_image_standardization(image)

    image_batch, label_batch = tf.train.batch([image, label],
                                                batch_size= batch_size,
                                                num_threads= 64, 
                                                capacity = capacity)

    #you can also use shuffle_batch 
#    image_batch, label_batch = tf.train.shuffle_batch([image,label],
#                                                      batch_size=BATCH_SIZE,
#                                                      num_threads=64,
#                                                      capacity=CAPACITY,
#                                                      min_after_dequeue=CAPACITY-1)

    label_batch = tf.reshape(label_batch, [batch_size])
    image_batch = tf.cast(image_batch, tf.float32)

    return image_batch, label_batch

错误是

INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.NotFoundError'>, NewRandomAccessFile failed to Create/Open: C:\Users\siqiz\Desktop\tensorflowLearing\01Catsvsdogs\traincat.2893.jpg : ???????????
; No such file or directory
         [[Node: ReadFile = ReadFile[_device="/job:localhost/replica:0/task:0/device:CPU:0"](input_producer/Gather)]]
Done training -- epoch limit reached
Traceback (most recent call last):

  File "<ipython-input-26-0683f80cdbe4>", line 1, in <module>
    run_training()

  File "C:/Users/siqiz/Desktop/tensorflowLearing/newCatAndDogs/01 cats vs dogs/training.py", line 95, in run_training
    coord.join(threads)

  File "C:\Users\siqiz\Anaconda3\lib\site-packages\tensorflow\python\training\coordinator.py", line 389, in join
    six.reraise(*self._exc_info_to_raise)

  File "C:\Users\siqiz\Anaconda3\lib\site-packages\six.py", line 693, in reraise
    raise value

  File "C:\Users\siqiz\Anaconda3\lib\site-packages\tensorflow\python\training\queue_runner_impl.py", line 252, in _run
    enqueue_callable()

  File "C:\Users\siqiz\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1259, in _single_operation_run
    None)

  File "C:\Users\siqiz\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 516, in __exit__
    c_api.TF_GetCode(self.status.status))

NotFoundError: NewRandomAccessFile failed to Create/Open: C:\Users\siqiz\Desktop\tensorflowLearing\01Catsvsdogs\traincat.2893.jpg : ???????????
; No such file or directory
     [[Node: ReadFile = ReadFile[_device="/job:localhost/replica:0/task:0/device:CPU:0"](input_producer/Gather)]]

Answer 1

仔细阅读此错误：“创建/打开失败：C：\ Users \ siqiz \ Desktop \ tensorflowLearing \ 01Catsvsdogs \ traincat.2893.jpg” 您的文件名必须是cat.2893.jpg，但是在这里，您的计算机识别出的文件名是“ traincat.2893.jpg”。

您可以尝试删除“ train_dir”末尾的“ \\”，如下所示： train_dir ='C：\ Users \ siqiz \ Desktop \ tensorflowLearing \ 01Catsvsdogs \ train'

我不确定它是否有效，因为我没有研究过Windows上的tensorflow，而是研究了Ubuntu.lol上的tensorflow

tensorflow：向协调员报告错误：<class'tensorflow.python.framework.errors_impl.notfounderror'=“”>

1 个答案: