def parse(record, is_training):
features = {
'image/encoded': tf.io.FixedLenFeature((), tf.string),
'image/class/label': tf.io.FixedLenFeature((), tf.int64),
'image/object/bbox/xmin': tf.io.VarLenFeature(dtype=tf.float32),
'image/object/bbox/ymin': tf.io.VarLenFeature(dtype=tf.float32),
'image/object/bbox/xmax': tf.io.VarLenFeature(dtype=tf.float32),
'image/object/bbox/ymax': tf.io.VarLenFeature(dtype=tf.float32),
}
parsed = tf.io.parse_single_example(record, features)
image_bytes = tf.reshape(parsed['image/encoded'], shape=[])
# bbox = tf.constant([0.0, 0.0, 1.0, 1.0], dtype=tf.float32, shape=[1, 1, 4])
bbox = tf.stack([
parsed['image/object/bbox/%s' % x].values
for x in ['ymin', 'xmin', 'ymax', 'xmax']
])
bbox = tf.transpose(tf.expand_dims(bbox, 0), [0, 2, 1])
image = resnet_preprocessing.preprocess_image(image_bytes,
bbox,
224,
224,
3,
is_training=is_training)
label = tf.cast(parsed['image/class/label'] - 1, tf.int32)
one_hot_label = tf.one_hot(label, depth=1000, dtype=tf.int32)
return image, one_hot_label
def _preprocess_image(image_bytes):
"""Preprocess a single raw image."""
image = tf.image.decode_image(tf.reshape(image_bytes, shape=[]), 3)
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
image = resnet_preprocessing.preprocess_image(image=image,
is_training=False)
return image
def _preprocess_image(image_bytes):
"""Preprocess a single raw image."""
image = resnet_preprocessing.preprocess_image(image_bytes=image_bytes,
is_training=False)
return image
