def set_training_random_scale_factors(self, scale_min, scale_max):
"""Set the parameters for multiscale training."""
# Select a random scale factor.
random_scale_factor = tf.random_uniform([], scale_min, scale_max)
scaled_size = tf.to_int32(random_scale_factor * self._output_size)
# Recompute the accurate scale_factor using rounded scaled image size.
height = tf.shape(self._image)[0]
width = tf.shape(self._image)[1]
max_image_size = tf.to_float(tf.maximum(height, width))
image_scale = tf.to_float(scaled_size) / max_image_size
# Select non-zero random offset (x, y) if scaled image is larger than
# self._output_size.
scaled_height = tf.to_int32(tf.to_float(height) * image_scale)
scaled_width = tf.to_int32(tf.to_float(width) * image_scale)
offset_y = tf.to_float(scaled_height - self._output_size)
offset_x = tf.to_float(scaled_width - self._output_size)
offset_y = tf.maximum(0.0, offset_y) * tf.random_uniform([], 0, 1)
offset_x = tf.maximum(0.0, offset_x) * tf.random_uniform([], 0, 1)
offset_y = tf.to_int32(offset_y)
offset_x = tf.to_int32(offset_x)
self._image_scale = image_scale
self._scaled_height = scaled_height
self._scaled_width = scaled_width
self._crop_offset_x = offset_x
self._crop_offset_y = offset_y
def set_scale_factors_to_output_size(self):
"""Set the parameters to resize input image to self._output_size."""
# Compute the scale_factor using rounded scaled image size.
height = tf.shape(self._image)[0]
width = tf.shape(self._image)[1]
max_image_size = tf.to_float(tf.maximum(height, width))
image_scale = tf.to_float(self._output_size) / max_image_size
scaled_height = tf.to_int32(tf.to_float(height) * image_scale)
scaled_width = tf.to_int32(tf.to_float(width) * image_scale)
self._image_scale = image_scale
self._scaled_height = scaled_height
self._scaled_width = scaled_width
def set_scale_factors_to_mlperf_reference_size(self):
"""Set the parameters to resize the image according to MLPerf reference."""
# Compute the scale_factor using rounded scaled image size.
height = tf.shape(self._image)[0]
width = tf.shape(self._image)[1]
# Recompute the accurate scale_factor using rounded scaled image size.
# https://github.com/ddkang/Detectron/blob/80f329530843e66d07ca39e19901d5f3e5daf009/lib/utils/blob.py#L70 # pylint: disable=line-too-long
min_image_size = tf.to_float(tf.minimum(height, width))
max_image_size = tf.to_float(tf.maximum(height, width))
short_side_scale = tf.to_float(
self._short_side_image_size) / min_image_size
long_side_scale = (tf.to_float(self._long_side_max_image_size) /
max_image_size)
image_scale = tf.minimum(short_side_scale, long_side_scale)
scaled_height = tf.to_int32(tf.to_float(height) * image_scale)
scaled_width = tf.to_int32(tf.to_float(width) * image_scale)
self._image_scale = image_scale
self._scaled_height = scaled_height
self._scaled_width = scaled_width
return image_scale
def _dataset_parser(value):
"""Parse data to a fixed dimension input image and learning targets.
Args:
value: A dictionary contains an image and groundtruth annotations.
Returns:
A list of the following elements in order:
image: Image tensor that is preproessed to have normalized value and
fixed dimension [image_size, image_size, 3]
label: label tensor of the same spatial dimension as the image.
"""
with tf.name_scope('parser'):
data = example_decoder.decode(value)
image = data['image']
label = data['labels_class']
label = tf.to_int32(label)
input_processor = SegmentationInputProcessor(
image, params['image_size'], label)
# The image normalization is identical to Cloud TPU ResNet.
input_processor.normalize_image()
if self._is_training and params['input_rand_hflip']:
input_processor.random_horizontal_flip()
if self._is_training:
input_processor.set_training_random_scale_factors(
params['train_scale_min'], params['train_scale_max'])
image = input_processor.resize_and_crop_image()
# Set padding to background (class=0) during training.
if self._is_training:
label = input_processor.resize_and_crop_label(0)
else:
label = input_processor.resize_and_crop_label(
params['ignore_label'])
if params['use_bfloat16']:
image = tf.cast(image, dtype=tf.bfloat16)
return image, label