Decoding tfrecord with tfslim

问题

I use Python 2.7.13 and Tensorflow 1.3.0 on CPU.

I want to use DensNet( https://github.com/pudae/tensorflow-densenet ) for regression problem. My data contains 60000 jpeg images with 37 float labels for each image. I saved my data into tfrecords files by:

def Read_Labels(label_path):
labels_csv = pd.read_csv(label_path)
labels = np.array(labels_csv)
return labels[:,1:]

def load_image(addr):
# read an image and resize to (224, 224)
img = cv2.imread(addr)
img = cv2.resize(img, (224, 224), interpolation=cv2.INTER_CUBIC)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = img.astype(np.float32)
return img

def Shuffle_images_with_labels(shuffle_data, photo_filenames, labels):
if shuffle_data:
    c = list(zip(photo_filenames, labels))
    shuffle(c)
    addrs, labels = zip(*c)
    return addrs, labels

def image_to_tfexample_mine(image_data, image_format, height, width, label):
return tf.train.Example(features=tf.train.Features(feature={
  'image/encoded': bytes_feature(image_data),    
  'image/format': bytes_feature(image_format),
  'image/class/label': _float_feature(label),
  'image/height': int64_feature(height),
  'image/width': int64_feature(width),
}))

def _convert_dataset(split_name, filenames, labels, dataset_dir):
assert split_name in ['train', 'validation']

num_per_shard = int(math.ceil(len(filenames) / float(_NUM_SHARDS)))

with tf.Graph().as_default():

    for shard_id in range(_NUM_SHARDS):
      output_filename = _get_dataset_filename(dataset_path, split_name, shard_id)

      with tf.python_io.TFRecordWriter(output_filename) as tfrecord_writer:
          start_ndx = shard_id * num_per_shard
          end_ndx = min((shard_id+1) * num_per_shard, len(filenames))
          for i in range(start_ndx, end_ndx):
              sys.stdout.write('\r>> Converting image %d/%d shard %d' % (
                      i+1, len(filenames), shard_id))
              sys.stdout.flush()

              img = load_image(filenames[i])
              image_data = tf.compat.as_bytes(img.tostring())

              label = labels[i]

              example = image_to_tfexample_mine(image_data, image_format, height, width, label)

              # Serialize to string and write on the file
              tfrecord_writer.write(example.SerializeToString())

sys.stdout.write('\n')
sys.stdout.flush()

def run(dataset_dir):

labels = Read_Labels(dataset_dir + '/training_labels.csv')

photo_filenames = _get_filenames_and_classes(dataset_dir + '/images_training')

shuffle_data = True 

photo_filenames, labels = Shuffle_images_with_labels(
        shuffle_data,photo_filenames, labels)

training_filenames = photo_filenames[_NUM_VALIDATION:]
training_labels = labels[_NUM_VALIDATION:]

validation_filenames = photo_filenames[:_NUM_VALIDATION]
validation_labels = labels[:_NUM_VALIDATION]

_convert_dataset('train',
                 training_filenames, training_labels, dataset_path)
_convert_dataset('validation',
                 validation_filenames, validation_labels, dataset_path)

print('\nFinished converting the Flowers dataset!')

And I decode it by:

with tf.Session() as sess:

feature = {
  'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
  'image/format': tf.FixedLenFeature((), tf.string, default_value='jpeg'),
  'image/class/label': tf.FixedLenFeature(
      [37,], tf.float32, default_value=tf.zeros([37,], dtype=tf.float32)),
   }

filename_queue = tf.train.string_input_producer([data_path], num_epochs=1)

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

features = tf.parse_single_example(serialized_example, features=feature)

image = tf.decode_raw(features['image/encoded'], tf.float32)
print(image.get_shape())

label = tf.cast(features['image/class/label'], tf.float32)

image = tf.reshape(image, [224, 224, 3])

images, labels = tf.train.shuffle_batch([image, label], batch_size=10, capacity=30, num_threads=1, min_after_dequeue=10)

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

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

for batch_index in range(6):
    img, lbl = sess.run([images, labels])
    img = img.astype(np.uint8)
    print(img.shape)
    for j in range(6):
        plt.subplot(2, 3, j+1)
        plt.imshow(img[j, ...])
    plt.show()

coord.request_stop()

coord.join(threads)

It's all fine up to this point. But when I use the bellow commands for decoding TFRecord files:

 reader = tf.TFRecordReader

keys_to_features = {
      'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
      'image/format': tf.FixedLenFeature((), tf.string, default_value='raw'),
      'image/class/label': tf.FixedLenFeature(
      [37,], tf.float32, default_value=tf.zeros([37,], dtype=tf.float32)),
      }

items_to_handlers = {
      'image': slim.tfexample_decoder.Image('image/encoded'),
      'label': slim.tfexample_decoder.Tensor('image/class/label'),
   }

decoder = slim.tfexample_decoder.TFExampleDecoder(
      keys_to_features, items_to_handlers)

I get the following error.

INFO:tensorflow:Error reported to Coordinator: , assertion failed: [Unable to decode bytes as JPEG, PNG, GIF, or BMP] [[Node: case/If_0/decode_image/cond_jpeg/cond_png/cond_gif/Assert_1/Assert = Assert[T=[DT_STRING], summarize=3, _device="/job:localhost/replica:0/task:0/cpu:0"](case/If_0/decode_image/cond_jpeg/cond_png/cond_gif/is_bmp, case/If_0/decode_image/cond_jpeg/cond_png/cond_gif/Assert_1/Assert/data_0)]] INFO:tensorflow:Caught OutOfRangeError. Stopping Training. INFO:sensorflow:Finished training! Saving model to disk.

To use Densenet for my problem, I should fix this error first. Could anybody please help me out of this problem. This code works perfectly for the datasets like flowers, MNIST and CIFAR10 available at https://github.com/pudae/tensorflow-densenet/tree/master/datasets but does not work for my data.

回答1:

Thanks to pudae, the problem is solved. I was needed to use:

 image_data = tf.gfile.FastGFile(filenames[i], 'rb').read()

Instead of this for loading data. That works perfectly now.

 img = load_image(filenames[i])
 image_data = tf.compat.as_bytes(img.tostring())

回答2:

According to the error, I think the problem is that you use an image decoder for array data (decoded data) because you saved decoded data when creating TFRecords. Maybe you have noticed, when you are not using slim, you use tf.decode_raw to decode the data. But when you use slim, the 'image/format': tf.FixedLenFeature((), tf.string, default_value='raw') is not used and by default, slim will use image decoder.

I believe you use the code in slim/data, where format_key = 'image/format' is you need. So, like this:

keys_to_features = {
    'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
    'image/format': tf.FixedLenFeature((), tf.string, default_value='raw'),
    'image/class/label': tf.FixedLenFeature(
        [1], tf.int64, default_value=tf.zeros([1], dtype=tf.int64)),
}

items_to_handlers = {
    'image': tfexample_decoder.Image(
      image_key = 'image/encoded',
      format_key = 'image/format',
    'label': tfexample_decoder.Tensor('image/class/label'),
}

decoder = tfexample_decoder.TFExampleDecoder(
    keys_to_features, items_to_handlers)

But I am not sure this can solve your problem perfectly because I can't reproduce your work in my machine.

来源：https://stackoverflow.com/questions/46687348/decoding-tfrecord-with-tfslim

标签

tensorflow

tf-slim

tfrecord