def _prepare_augmented_batch(self, tensors, batch_size, image_size=None):
if self.subset == "train":
assert batch_size == 1, "only implemented for 1 so far"
augmentor_strs = self.config.unicode_list("augmentors_train", [])
augmentors = parse_augmentors(augmentor_strs, self.void_label())
for augmentor in augmentors:
tensors = augmentor.apply(tensors)
if image_size is None:
image_size = self.image_size
tensors = assemble_input_tensors(tensors, image_size)
# batchify
keys = tensors.keys()
tensors = {k: tf.expand_dims(tensors[k], axis=0) for k in keys}
else:
augmentor_strs = self.config.unicode_list("augmentors_val", [])
assert "scale" not in augmentor_strs, "scale augmentation during test time not implemented yet"
assert "translation" not in augmentor_strs, "translation augmentation during test time not implemented yet"
augmentors = parse_augmentors(augmentor_strs, self.void_label())
tensors = [tensors for _ in xrange(batch_size)]
tensors = [apply_augmentors(t, augmentors) for t in tensors]
tensors = [assemble_input_tensors(t) for t in tensors]
# batchify
keys = tensors[0].keys()
tensors = {
k: tf.stack([t[k] for t in tensors], axis=0)
for k in keys
}
return tensors
def _prepare_augmented_batch(self, tensors, batch_size, image_size=None):
if self.subset == "train":
assert batch_size == 1, "only implemented for 1 so far"
augmentor_strs = self.config.unicode_list("augmentors_train", [])
augmentors = parse_augmentors(augmentor_strs, self.void_label())
for augmentor in augmentors:
tensors = augmentor.apply(tensors)
if image_size is None:
image_size = self.image_size
tensors = assemble_input_tensors(tensors, image_size)
# batchify
keys = list(tensors.keys())
tensors = {k: tf.expand_dims(tensors[k], axis=0) for k in keys}
# for testing
# from datasets.Util.Normalization import unnormalize
# summ0 = tf.summary.image("inputs", unnormalize(tensors["inputs"][:, :, :, :3]))
# summ1 = tf.summary.image("labels", tensors["labels"] * 255)
# summ2 = tf.summary.image("old_labels", tensors["inputs"][:, :, :, 3:4])
# flow0 = tensors["inputs"][:, :, :, 4:5]
# flow0 -= tf.reduce_min(flow0)
# flow0 /= tf.reduce_max(flow0)
# flow1 = tensors["inputs"][:, :, :, 5:6]
# flow1 -= tf.reduce_min(flow1)
# flow1 /= tf.reduce_max(flow1)
# summ3 = tf.summary.image("flow_future_3", flow3)
# summ4 = tf.summary.image("flow_future_4", flow4)
# self.summaries += [summ0, summ1, summ2, summ3, summ4]
else:
augmentor_strs = self.config.unicode_list("augmentors_val", [])
assert "scale" not in augmentor_strs, "scale augmentation during test time not implemented yet"
assert "translation" not in augmentor_strs, "translation augmentation during test time not implemented yet"
augmentors = parse_augmentors(augmentor_strs, self.void_label())
tensors = [tensors for _ in range(batch_size)]
tensors = [apply_augmentors(t, augmentors) for t in tensors]
tensors = [assemble_input_tensors(t) for t in tensors]
# batchify
keys = list(tensors[0].keys())
tensors = {
k: tf.stack([t[k] for t in tensors], axis=0)
for k in keys
}
return tensors
def _read_inputfiles(self, queue, resize_mode, input_size, augmentors):
im_path = queue[0]
label_path = queue[1]
old_label_path = queue[2]
img = load_image_tensorflow(im_path, jpg=True)
old_label = load_png_mask_tensorflow(old_label_path)
def my_damage_mask(mask):
return damage_mask(mask, self.old_mask_scale_factor,
self.old_mask_shift_absolute,
self.old_mask_shift_factor)
old_label, = tf.py_func(my_damage_mask, [old_label], [tf.float32])
label = load_png_mask_tensorflow(label_path)
flow_past = flow_future = None
if self.flow_into_past:
flow_past_path = queue[3]
flow_past = load_flow_from_flo_tensorflow(flow_past_path,
self.flow_as_angle)
if self.flow_into_future:
flow_future_path = queue[4] if self.flow_into_past else queue[3]
flow_future = load_flow_from_flo_tensorflow(
flow_future_path, self.flow_as_angle)
tensors = create_tensor_dict(unnormalized_img=img,
label=label,
tag=im_path,
raw_label=label,
old_label=old_label,
flow_past=flow_past,
flow_future=flow_future)
resize_mode, input_size = self._get_resize_params(
self.subset, self.image_size)
tensors = resize(tensors, resize_mode, input_size)
for augmentor in augmentors:
tensors = augmentor.apply(tensors)
tensors = assemble_input_tensors(tensors, DAVIS_IMAGE_SIZE)
label.set_shape(list(DAVIS_IMAGE_SIZE) + [1])
summaries = []
return tensors, summaries
def read_images_from_disk(
input_queue,
input_size,
resize_mode,
label_postproc_fn=lambda x: x,
augmentors=(),
label_load_fn=load_label_default,
img_load_fn=load_img_default,
distance_transform_fn=Util.create_distance_transform):
im_path = input_queue[0]
label_path = input_queue[1]
if len(input_queue) > 2:
img_id = input_queue[2]
else:
img_id = None
img = img_load_fn(img_path=im_path)
#TODO: clean up all this stuff!
labels = label_load_fn(im_path, label_path)
if 'label' in list(labels.keys()):
label = labels['label']
label = label_postproc_fn(label)
label.set_shape(img.get_shape().as_list()[:-1] + [1])
else:
label = None
if 'old_label' in list(labels.keys()):
old_label = labels['old_label']
old_label.set_shape(img.get_shape().as_list()[:-1] + [1])
else:
old_label = None
if Constants.BBOXES in list(labels.keys()):
bboxes = labels[Constants.BBOXES]
else:
bboxes = None
if Constants.IDS in list(labels.keys()):
ids = labels[Constants.IDS]
else:
ids = None
if Constants.CLASSES in list(labels.keys()):
classes = labels[Constants.CLASSES]
else:
classes = None
if Constants.IGNORE_REGIONS in list(labels.keys()):
ignore_regions = labels[Constants.IGNORE_REGIONS]
else:
ignore_regions = None
if Constants.SCENE_INFOS in list(labels.keys()):
scene_infos = labels[Constants.SCENE_INFOS]
else:
scene_infos = None
if Constants.OLD_LABEL_AS_DT in list(labels.keys()):
old_label_as_dt = labels[Constants.OLD_LABEL_AS_DT]
else:
old_label_as_dt = None
u0 = None
u1 = None
tensors = create_tensor_dict(unnormalized_img=img,
label=label,
old_label=old_label,
u0=u0,
u1=u1,
tag=im_path,
raw_label=label,
bboxes=bboxes,
ids=ids,
classes=classes,
img_id=img_id,
ignore_regions=ignore_regions,
scene_infos=scene_infos,
old_label_as_dt=old_label_as_dt)
tensors = resize(tensors, resize_mode, input_size)
# Create distance transform after image resize to speed up the computation.
if Constants.USE_CLICKS in list(labels.keys()):
assert Constants.STRATEGY in labels and Constants.IGNORE_CLASSES in labels
tensors = add_distance_transform(tensors, labels,
distance_transform_fn)
elif Constants.OLD_LABEL_AS_DT in list(labels.keys()):
tensors["old_label"] = tf.py_func(distance_transform_fn,
[tensors["label"]], [tf.float32])[0]
tensors["old_label"].set_shape(tensors["label"].get_shape())
tensors = apply_augmentors(tensors, augmentors)
tensors = assemble_input_tensors(tensors)
summaries = []
return tensors, summaries
def read_images_from_disk(input_queue,
input_size,
resize_mode,
label_postproc_fn=lambda x: x,
augmentors=(),
label_load_fn=load_label_default,
img_load_fn=load_img_default):
im_path = input_queue[0]
label_path = input_queue[1]
img = img_load_fn(img_path=im_path)
labels = label_load_fn(im_path, label_path)
label = labels['label']
label = label_postproc_fn(label)
label.set_shape(img.get_shape().as_list()[:-1] + [1])
old_label = u0 = u1 = None
if len(input_queue) == 3:
flow_path = input_queue[2]
flow = img_load_fn(img_path=flow_path)
else:
flow = None
if 'old_label' in labels.keys():
old_label = labels['old_label']
old_label.set_shape(img.get_shape().as_list()[:-1] + [1])
if Constants.DT_NEG in labels.keys() and Constants.DT_POS in labels.keys():
u0 = labels[Constants.DT_NEG]
u0.set_shape(img.get_shape().as_list()[:-1] + [1])
# Create a negative click map, where the click points are denoted as 1 and the rest of it as 0.
# This would majorly be used to show the clicks in summaries.
[neg_clicks] = tf.py_func(create_clicks_map,
[labels['neg_clicks'], u0], [tf.float32],
name="create_click_map")
neg_clicks.set_shape(img.get_shape().as_list()[:-1] + [1])
u0 = tf.concat([u0, neg_clicks], axis=2)
u1 = labels[Constants.DT_POS]
u1.set_shape(img.get_shape().as_list()[:-1] + [1])
[pos_clicks] = tf.py_func(create_clicks_map,
[labels['pos_clicks'], u1], [tf.float32],
name="create_click_map")
pos_clicks.set_shape(img.get_shape().as_list()[:-1] + [1])
u1 = tf.concat([u1, pos_clicks], axis=2)
shape = im_path.get_shape()
im_path = tf.string_join(
[im_path, tf.as_string(labels['num_clicks'])],
separator=":",
name="JoinPath")
im_path.set_shape(shape)
tensors = create_tensor_dict(unnormalized_img=img,
label=label,
old_label=old_label,
u0=u0,
u1=u1,
tag=im_path,
raw_label=label,
flow=flow)
tensors = resize(tensors, resize_mode, input_size)
tensors = apply_augmentors(tensors, augmentors)
tensors = assemble_input_tensors(tensors)
summaries = []
return tensors, summaries