Feature-Format-Fehler beim Lesen von tfrecord (Kann ein ndarray nicht in einen Tensor oder eine Operation konvertieren)

Question

Ich habe lange an der Erstellung meiner eigenen Datenbank gearbeitet, um ein CNN zu trainieren. Jetzt habe ich ein Problem mit dem Lesen von Daten aus der Tfrecord-Datei. Ich habe erfolgreich eine TFrecord-Datei gespeichert, die zwei Funktionen enthält: Bild und Label. Wenn ich versuche, es zu lesen, liest es nur den ersten Stapel und dann erhalte ich eine Fehlermeldung.

Der Code der tfrecord Datei zum Speichern (I wegen Zeit nur 5 Dateien angenommen):

#SAVE TFRECORD FILE 

import tensorflow as tf 
import numpy as np 
import Image 

image_filename = [('/home/ag/Dropbox/DL/6_CNN_BD/data_resized/01GraspableGraspingRectangles_RGB/00%03d.png' % x) for x in range(1,6)] 

records_filename = '/home/ag/Dropbox/DL/6_CNN_BD/data_resized/01GraspableGraspingRectangles_RGB/DS.tfrecord' 
writer = tf.python_io.TFRecordWriter(records_filename) 

original_images = [] 

for img_path in image_filename: 

    image = np.array(Image.open(img_path)) 
    #img_label = 'GP' 
    img_label = b'\x01' 
    img_raw = image.tostring() 

    example = tf.train.Example(features=tf.train.Features(feature={ 
     'image_raw': tf.train.Feature(bytes_list = tf.train.BytesList(value = [img_raw])), 
     'label': tf.train.Feature(bytes_list = tf.train.BytesList(value = [img_label])), 
     })) 

    writer.write(example.SerializeToString()) 

writer.close() 

Der Code, der tfrecord Datei zum Lesen ist:

#READ TFRECORD FILE 

import tensorflow as tf 
import skimage.io as io 

IMAGE_HEIGHT = 24 
IMAGE_WIDTH = 24 
IMAGE_CHANNELS = 3 
BATCH_SIZE = 2 

tfrecords_filename = '/home/ag/Dropbox/DL/6_CNN_BD/data_resized/01GraspableGraspingRectangles_RGB/DS.tfrecord' 

def read_and_decode(filename_queue): 

    reader = tf.TFRecordReader() 
    _, serialized_example = reader.read(filename_queue) 

    features = tf.parse_single_example(
     serialized_example, features={ 
      'image_raw': tf.FixedLenFeature([], tf.string), 
      'label': tf.FixedLenFeature([], tf.string), 
     }) 

    image = tf.decode_raw(features['image_raw'], tf.uint8) 
    image_reshape = tf.reshape(image, [IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNELS]) 

    label = tf.cast(features['label'], tf.string) 
    label_reshape = label 

    images, label = tf.train.shuffle_batch([image_reshape, label_reshape], 
              batch_size = 2, 
              capacity = 30, 
              num_threads = 2, 
              min_after_dequeue = 10) 
    return images, label 


filename_queue = tf.train.string_input_producer([tfrecords_filename], num_epochs=10) 
image, label = read_and_decode(filename_queue) 

init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) 

with tf.Session() as sess: 

    sess.run(init_op) 

    coord = tf.train.Coordinator() 
    threads = tf.train.start_queue_runners(coord = coord) 

    for i in range(5): 

     img, label = sess.run([image, label]) 
     print(img.shape) 
     print(label) 

     print('current batch') 

     io.imshow(img[0, :, :, :]) 
     io.show() 

     io.imshow(img[1, :, :, :]) 
     io.show() 

    coord.request_stop() 
    coord.join(threads) 

Es ist wichtig, Erwähnen Sie, dass, wenn ich img, label = sess.run([image, label]) für img = sess.run(image) ändern, habe ich keinen Fehler. Das lässt mich glauben, dass das Problem mit dem Format der Label-Funktion zusammenhängt.

Der Fehlerbildschirm ähnelt:

>>> 
(2, 24, 24, 3) 
['\x01' '\x01'] 
current batch 

Traceback (most recent call last): 
    File "/home/ag/Dropbox/DL/6_CNN_BD/DS2.py", line 52, in <module> 
    img, label = sess.run([image, label]) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 767, in run 
    run_metadata_ptr) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 952, in _run 
    fetch_handler = _FetchHandler(self._graph, fetches, feed_dict_string) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 408, in __init__ 
    self._fetch_mapper = _FetchMapper.for_fetch(fetches) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 230, in for_fetch 
    return _ListFetchMapper(fetch) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 337, in __init__ 
    self._mappers = [_FetchMapper.for_fetch(fetch) for fetch in fetches] 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 238, in for_fetch 
    return _ElementFetchMapper(fetches, contraction_fn) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 271, in __init__ 
    % (fetch, type(fetch), str(e))) 
TypeError: Fetch argument array(['\x01', '\x01'], dtype=object) has invalid type <type 'numpy.ndarray'>, must be a string or Tensor. (Can not convert a ndarray into a Tensor or Operation.) 

ich auf unterschiedliche Weise, aber ohne Erfolg versucht haben. Irgendwelche Vorschläge für dieses Problem?

Answer 1

Hier ist der Code, mit einigen kleinen Änderungen, die geholfen haben, das Problem zu beheben.

#READ TFRECORD FILE 

import tensorflow as tf 
import skimage.io as io 
import Image 

IMAGE_HEIGHT = 24 
IMAGE_WIDTH = 24 
IMAGE_CHANNELS = 3 
BATCH_SIZE = 5 
MIN_AFTER_DEQUEUE = 10000 
CAPACITY = MIN_AFTER_DEQUEUE+3*BATCH_SIZE 
NUM_THREADS = 2 

tfrecords_filename = ['/home/ag/Dropbox/DL/6_CNN_BD/data_resized/TFrecords/DS01.tfrecord', '/home/ag/Dropbox/DL/6_CNN_BD/data_resized/TFrecords/DS02.tfrecord'] 

def read_and_decode(filename_queue): 

    reader = tf.TFRecordReader() 
    _, serialized_example = reader.read(filename_queue) 

    features = tf.parse_single_example(
     serialized_example, features={ 
      'image_raw': tf.FixedLenFeature([], tf.string), 
      'label': tf.FixedLenFeature([], tf.string), 
     }) 

    image = tf.decode_raw(features['image_raw'], tf.uint8) 
    image_reshape = tf.reshape(image, [IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNELS]) 

    label = tf.cast(features['label'], tf.string) 
    label_reshape = label 

    images, label = tf.train.shuffle_batch([image_reshape, label_reshape], 
              batch_size = BATCH_SIZE, 
              capacity = CAPACITY, 
              num_threads = NUM_THREADS, 
              min_after_dequeue = MIN_AFTER_DEQUEUE) 
    #images, label = tf.train.batch([image_reshape, label_reshape], batch_size = 2, capacity = 30, num_threads = 2, min_after_dequeue = 10) 

    return images, label 
    #return image_reshape, label_reshape 

filename_queue = tf.train.string_input_producer(tfrecords_filename, num_epochs=10) 
image, label = read_and_decode(filename_queue) 

init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) 

with tf.Session() as sess: 

    sess.run(init_op) 

    coord = tf.train.Coordinator() 
    threads = tf.train.start_queue_runners(coord = coord) 

    for i in range(1000): 

     img, lbl = sess.run([image, label]) 
     print(i, img.shape, lbl) 

     print('current batch') 

     #img_save = Image.fromarray(img, 'RGB')  
     #img_save.save("/home/ag/Dropbox/DL/6_CNN_BD/data_resized/02GraspableGraspingRectangles_RGB/" + str(i) + "-train.png") 

     #io.imshow(img[0, :, :, :]) 
     #io.show() 

     #io.imshow(img[1, :, :, :]) 
     #io.show() 

    coord.request_stop() 
    coord.join(threads)