class ImageCoder(object):
"""Helper class that provides TensorFlow image coding utilities."""def __init__(self):
# Create a single Session to run all image coding calls.
self._sess = tf.Session()# Initializes function that converts PNG to JPEG data.
self._png_data = https://www.it610.com/article/tf.placeholder(dtype=tf.string)
image = tf.image.decode_png(self._png_data, channels=3)
self._png_to_jpeg = tf.image.encode_jpeg(image, format='rgb', quality=100)# Initializes function that decodes RGB JPEG data.
self._decode_jpeg_data = tf.placeholder(dtype=tf.string)
self._decode_jpeg = tf.image.decode_jpeg(self._decode_jpeg_data, channels=3)def png_to_jpeg(self, image_data):
return self._sess.run(self._png_to_jpeg,
feed_dict={self._png_data: image_data})def decode_jpeg(self, image_data):
image = self._sess.run(self._decode_jpeg,
feed_dict={self._decode_jpeg_data: image_data})
assert len(image.shape) == 3
assert image.shape[2] == 3
return image
def _process_image(filename, coder):
"""Process a single image file.
Args:
filename: string, path to an image file e.g., '/path/to/example.JPG'.
coder: instance of ImageCoder to provide TensorFlow image coding utils.
Returns:
image_buffer: string, JPEG encoding of RGB image.
height: integer, image height in pixels.
width: integer, image width in pixels.
"""
# Read the image file.
with open(filename, 'r') as f:
image_data = https://www.it610.com/article/f.read()# Convert any PNG to JPEG's for consistency.
if _is_png(filename):
logging.info('Converting PNG to JPEG for %s' % filename)
image_data = https://www.it610.com/article/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]
assert image.shape[2] == 3return image_data, height, width
def _convert_to_example(filename, image_buffer, label, text, height, width):
"""Build an Example proto for an example.
Args:
filename: string, path to an image file, e.g., '/path/to/example.JPG'
image_buffer: string, JPEG encoding of RGB image
label: integer, identifier for the ground truth for the network
text: string, unique human-readable, e.g. 'dog'
height: integer, image height in pixels
width: integer, image width in pixels
Returns:
Example proto
"""colorspace = 'RGB'
channels = 3
image_format = 'JPEG'example = tf.train.Example(features=tf.train.Features(feature={
'image/height': _int64_feature(height),
'image/width': _int64_feature(width),
'image/colorspace': _bytes_feature(colorspace),
'image/channels': _int64_feature(channels),
'image/class/label': _int64_feature(label),
'image/class/text': _bytes_feature(text),
'image/format': _bytes_feature(image_format),
'image/filename': _bytes_feature(os.path.basename(filename)),
'image/encoded': _bytes_feature(image_buffer)}))
return example
