def _parse_eval_data(self, data):
"""Parses data for evaluation."""
# Get the image shape constants and cast the image to the selcted datatype.
image = tf.cast(data['image'], dtype=self._dtype)
boxes = data['groundtruth_boxes']
classes = data['groundtruth_classes']
image, infos, _ = preprocessing_ops.resize_and_jitter_image(
image, [self._image_h, self._image_w],
letter_box=self._letter_box,
random_pad=False,
shiftx=0.5,
shifty=0.5,
jitter=0.0)
# Clip and clean boxes.
image = image / 255.0
boxes, inds = preprocessing_ops.transform_and_clip_boxes(
boxes,
infos,
shuffle_boxes=False,
area_thresh=0.0,
filter_and_clip_boxes=False)
classes = tf.gather(classes, inds)
info = infos[-1]
image, labels = self._build_label(image,
boxes,
classes,
info,
inds,
data,
is_training=False)
return image, labels
def testResizeAndJitterImage(self, image_height, image_width, desired_size):
image = tf.convert_to_tensor(np.random.rand(image_height, image_width, 3))
processed_image, _, _ = preprocessing_ops.resize_and_jitter_image(
image, desired_size)
processed_image_shape = tf.shape(processed_image)
self.assertAllEqual([desired_size[0], desired_size[1], 3],
processed_image_shape.numpy())
def _jitter_scale(self, image, shape, letter_box, jitter, random_pad,
aug_scale_min, aug_scale_max, translate, angle,
perspective):
"""Distort and scale each input image."""
infos = []
if (aug_scale_min != 1.0 or aug_scale_max != 1.0):
crop_only = True
# jitter gives you only one info object, resize and crop gives you one,
# if crop only then there can be 1 form jitter and 1 from crop
infos.append(self._pad_infos_object(image))
else:
crop_only = False
image, crop_info, _ = preprocessing_ops.resize_and_jitter_image(
image,
shape,
letter_box=letter_box,
jitter=jitter,
crop_only=crop_only,
random_pad=random_pad,
seed=self._seed,
)
infos.extend(crop_info)
image, _, affine = preprocessing_ops.affine_warp_image(
image,
shape,
scale_min=aug_scale_min,
scale_max=aug_scale_max,
translate=translate,
degrees=angle,
perspective=perspective,
random_pad=random_pad,
seed=self._seed,
)
return image, infos, affine
def _augment_image(self,
image,
boxes,
classes,
is_crowd,
area,
xs=0.0,
ys=0.0,
cut=None):
"""Process a single image prior to the application of patching."""
if self._random_flip:
# Randomly flip the image horizontally.
image, boxes, _ = preprocess_ops.random_horizontal_flip(
image, boxes, seed=self._seed)
# Augment the image without resizing
image, infos, crop_points = preprocessing_ops.resize_and_jitter_image(
image, [self._output_size[0], self._output_size[1]],
random_pad=False,
letter_box=self._letter_box,
jitter=self._random_crop,
shiftx=xs,
shifty=ys,
cut=cut,
seed=self._seed)
# Clip and clean boxes.
boxes, inds = preprocessing_ops.transform_and_clip_boxes(
boxes,
infos,
area_thresh=self._area_thresh,
shuffle_boxes=False,
filter_and_clip_boxes=True,
seed=self._seed)
classes, is_crowd, area = self._select_ind(inds, classes, is_crowd,
area) # pylint:disable=unbalanced-tuple-unpacking
return image, boxes, classes, is_crowd, area, crop_points
