def get_image_info(self):
"""Returns image information for scaled and original height and width."""
return tf.stack([
tf.to_float(self._scaled_height),
tf.to_float(self._scaled_width), 1.0 / self._image_scale,
tf.to_float(self._ori_height),
tf.to_float(self._ori_width)
])
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_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 _dataset_parser(value):
"""Parse data to a fixed dimension input image and learning targets."""
with tf.name_scope('parser'):
data = example_decoder.decode(value)
source_id = data['source_id']
image = data['image']
boxes = data['groundtruth_boxes']
classes = data['groundtruth_classes']
classes = tf.reshape(tf.cast(classes, dtype=tf.float32),
[-1, 1])
# the image normalization is identical to Cloud TPU ResNet-50
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
image = _normalize_image(image)
if params['input_rand_hflip']:
image, boxes = preprocessor.random_horizontal_flip(
image, boxes=boxes)
image_original_shape = tf.shape(image)
image, _ = preprocessor.resize_to_range(
image,
min_dimension=params['image_size'],
max_dimension=params['image_size'])
image_scale = tf.to_float(
image_original_shape[0]) / tf.to_float(tf.shape(image)[0])
image, boxes = preprocessor.scale_boxes_to_pixel_coordinates(
image, boxes, keypoints=None)
image = tf.image.pad_to_bounding_box(image, 0, 0,
params['image_size'],
params['image_size'])
(cls_targets, box_targets,
num_positives) = anchor_labeler.label_anchors(boxes, classes)
source_id = tf.string_to_number(source_id, out_type=tf.float32)
row = (image, cls_targets, box_targets, num_positives,
source_id, image_scale)
return row
def resize_and_crop_boxes(self):
"""Resize boxes and crop it to the self._output dimension."""
boxlist = preprocessor.box_list.BoxList(self._boxes)
boxes = preprocessor.box_list_scale(
boxlist, self._scaled_height, self._scaled_width).get()
# Adjust box coordinates based on the offset.
box_offset = tf.stack([self._crop_offset_y, self._crop_offset_x,
self._crop_offset_y, self._crop_offset_x,])
boxes -= tf.to_float(tf.reshape(box_offset, [1, 4]))
# Clip the boxes.
boxes = self.clip_boxes(boxes)
# Filter out ground truth boxes that are all zeros.
indices = tf.where(tf.not_equal(tf.reduce_sum(boxes, axis=1), 0))
boxes = tf.gather_nd(boxes, indices)
classes = tf.gather_nd(self._classes, indices)
return boxes, classes
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
