我试图为我的语义分割数据集(rgb_image_in-> binary_raycast_out)创建tfrecords。
下面是我的代码,用于将图像列表写入train.tfrecord。
def _process_image_files(image_names, raycast_names):
writer = tf.python_io.TFRecordWriter('train')
#My implementation of decoding jpeg/png image
coder = ImageCoder()
for i in range(len(image_names)):
print('{}\n{}\n\n'.format(image_names[i], raycast_names[i]))
image_buffer, im_height, im_width, im_channels = _process_image(image_names[i], coder)
raycast_buffer, rc_height, rc_width, rc_channels = _process_image(raycast_names[i], coder)
example = _convert_to_example(image_names[i], raycast_names[i], image_buffer, raycast_buffer, \
im_height, im_width, im_channels)
writer.write(example.SerializeToString())
writer.close()
sys.stdout.flush()
def _process_image(filename, coder):
with tf.gfile.FastGFile(filename, 'rb') as f:
image_data = f.read()
# Convert any PNG to JPEG's for consistency.
if _is_png(filename):
print('Converting PNG to JPEG for %s' % filename)
image_data = coder.png_to_jpeg(image_data)
# Decode the RGB JPEG.
image = coder.decode_jpeg(image_data)
# Check that image converted to RGB
assert len(image.shape) == 3
height = image.shape[0]
width = image.shape[1]
channels = image.shape[2]
assert channels == 3
return image_data, height, width, channels
def _convert_to_example(image_name, raycast_name, image_buffer, raycast_buffer, sample_height, sample_width, sample_channels):
example = tf.train.Example(features=tf.train.Features(feature={
'height': _int64_feature(sample_height),
'width': _int64_feature(sample_width),
'channels': _int64_feature(sample_channels),
'image/filename': _bytes_feature(tf.compat.as_bytes(image_name)),
'image/encoded': _bytes_feature(tf.compat.as_bytes(image_buffer)),
'raycast/filename': _bytes_feature(tf.compat.as_bytes(raycast_name)),
'raycast/encoded': _bytes_feature(tf.compat.as_bytes(raycast_buffer))}))
return example
上面的代码在创建tfrecord文件时效果很好。我在_convert_to_example
方法中放入了一些打印语句,以确保在一个示例中写入了相应的文件名(image_file和raycast_file)。
但是,当我从tfrecord阅读示例并打印图像名称时,看起来image_file和raycast_file名称不对应。 tfRecordReader()读取的图像对是错误的。
下面是我读取记录的代码:
def parse_example_proto(example_serialized):
feature_map = {
'image/encoded': tf.FixedLenFeature([], dtype=tf.string, default_value=''),
'raycast/encoded': tf.FixedLenFeature([], dtype=tf.string, default_value=''),
'height': tf.FixedLenFeature([1], dtype=tf.int64, default_value=-1),
'width': tf.FixedLenFeature([1], dtype=tf.int64, default_value=-1),
'channels': tf.FixedLenFeature([1], dtype=tf.int64, default_value=-1),
'image/filename': tf.FixedLenFeature([], dtype=tf.string, default_value=''),
'raycast/filename': tf.FixedLenFeature([], dtype=tf.string, default_value='')
}
features = tf.parse_single_example(example_serialized, feature_map)
return features['image/encoded'], features['raycast/encoded'], \
features['height'], features['width'], features['channels'],\
features['image/filename'], features['raycast/filename']
def retirieve_samples():
with tf.name_scope('batch_processing'):
data_files = ['train']
filename_queue = tf.train.string_input_producer(data_files, shuffle=False)
reader = tf.TFRecordReader()
_, example_serialized = reader.read(filename_queue)
image_buffer, raycast_buffer, height, width, channels, image_name, raycast_name = parse_example_proto(example_serialized)
orig_image = tf.image.resize_images(tf.image.decode_jpeg(image_buffer, channels=3),
[480, 856])
orig_raycast = tf.image.resize_images(tf.image.decode_jpeg(raycast_buffer, channels=3),
[480, 856])
return image_name, raycast_name
下面是我的打印一对文件名的代码
image_name, raycast_name = retirieve_samples()
with tf.Session() as sess:
for i in range(1):
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
print(sess.run(image_name))
print(sess.run(raycast_name))
coord.request_stop()
coord.join(threads)
我花了几天时间。我无法确定为什么我无法检索正确的货币对。正在检索的示例应该与正在创建的示例具有相同的数据,对吗?为什么在读写时看到不同的名称对?
任何帮助都将得到
答案 0 :(得分:1)
一个较小的示例会更好。
每个image_name
将评估张量并运行图。这意味着,如果分别评估raycast_name
和current_image_name, current_raycast_name = session.run([
image_name, raycast_name
])
,则会从不同的运行次数中获得它们,而它们将不是一对。
您可以通过同时评估两者来获得一对,例如:
alt
我还建议在队列中使用较新的Dataset API。