def preproc_img(fname, boxes, klass, second_klass, is_crowd, aug):
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
# rpn anchor:
try:
fm_labels, fm_boxes = get_rpn_anchor_input(im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
if config.USE_SECOND_HEAD:
second_klass = second_klass[is_crowd == 0]
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once("Input {} is filtered for training: {}".format(fname, str(e)),
'warn')
return None
if config.USE_SECOND_HEAD:
ret = [im, fm_labels, fm_boxes, boxes, klass, second_klass]
else:
ret = [im, fm_labels, fm_boxes, boxes, klass]
return ret, params
def preprocess(roidb):
fname, boxes, klass, is_crowd = roidb['file_name'], roidb[
'boxes'], roidb['class'], roidb['is_crowd']
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
ret = {'image': im}
# rpn anchor:
try:
ret['anchor_labels'], ret['anchor_boxes'] = get_rpn_anchor_input(
im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
ret['gt_boxes'] = boxes
ret['gt_labels'] = klass
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once(
"Input {} is filtered for training: {}".format(fname, str(e)),
'warn')
return None
return ret
def preprocess(roidb):
fname, boxes, klass, is_crowd = roidb['file_name'], roidb['boxes'], roidb['class'], roidb['is_crowd']
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
ret = {'image': im}
# rpn anchor:
try:
if cfg.MODE_FPN:
multilevel_anchor_inputs = get_multilevel_rpn_anchor_input(im, boxes, is_crowd)
for i, (anchor_labels, anchor_boxes) in enumerate(multilevel_anchor_inputs):
ret['anchor_labels_lvl{}'.format(i + 2)] = anchor_labels
ret['anchor_boxes_lvl{}'.format(i + 2)] = anchor_boxes
else:
# anchor_labels, anchor_boxes
ret['anchor_labels'], ret['anchor_boxes'] = get_rpn_anchor_input(im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
ret['gt_boxes'] = boxes
ret['gt_labels'] = klass
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once("Input {} is filtered for training: {}".format(fname, str(e)), 'warn')
return None
if cfg.MODE_MASK:
# augmentation will modify the polys in-place
segmentation = copy.deepcopy(roidb['segmentation'])
segmentation = [segmentation[k] for k in range(len(segmentation)) if not is_crowd[k]]
assert len(segmentation) == len(boxes)
# Apply augmentation on polygon coordinates.
# And produce one image-sized binary mask per box.
masks = []
for polys in segmentation:
polys = [aug.augment_coords(p, params) for p in polys]
masks.append(segmentation_to_mask(polys, im.shape[0], im.shape[1]))
masks = np.asarray(masks, dtype='uint8') # values in {0, 1}
ret['gt_masks'] = masks
# from viz import draw_annotation, draw_mask
# viz = draw_annotation(im, boxes, klass)
# for mask in masks:
# viz = draw_mask(viz, mask)
# tpviz.interactive_imshow(viz)
return ret
def preprocess(roidb):
fname, boxes, klass, is_crowd = roidb['file_name'], roidb['boxes'], roidb['class'], roidb['is_crowd']
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
ret = {'image': im}
# rpn anchor:
try:
if cfg.MODE_FPN:
multilevel_anchor_inputs = get_multilevel_rpn_anchor_input(im, boxes, is_crowd)
for i, (anchor_labels, anchor_boxes) in enumerate(multilevel_anchor_inputs):
ret['anchor_labels_lvl{}'.format(i + 2)] = anchor_labels
ret['anchor_boxes_lvl{}'.format(i + 2)] = anchor_boxes
else:
# anchor_labels, anchor_boxes
ret['anchor_labels'], ret['anchor_boxes'] = get_rpn_anchor_input(im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
ret['gt_boxes'] = boxes
ret['gt_labels'] = klass
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once("Input {} is filtered for training: {}".format(fname, str(e)), 'warn')
return None
if cfg.MODE_MASK:
# augmentation will modify the polys in-place
segmentation = copy.deepcopy(roidb['segmentation'])
segmentation = [segmentation[k] for k in range(len(segmentation)) if not is_crowd[k]]
assert len(segmentation) == len(boxes)
# Apply augmentation on polygon coordinates.
# And produce one image-sized binary mask per box.
masks = []
for polys in segmentation:
polys = [aug.augment_coords(p, params) for p in polys]
masks.append(segmentation_to_mask(polys, im.shape[0], im.shape[1]))
masks = np.asarray(masks, dtype='uint8') # values in {0, 1}
ret['gt_masks'] = masks
# from viz import draw_annotation, draw_mask
# viz = draw_annotation(im, boxes, klass)
# for mask in masks:
# viz = draw_mask(viz, mask)
# tpviz.interactive_imshow(viz)
return ret
def _augment_boxes(boxes, aug, params):
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
#assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
if np.min(np_area(boxes)) <= 0:
return None
return boxes
def preprocess(img):
fname, boxes, klass, is_crowd = img['file_name'], img['boxes'], img['class'], img['is_crowd']
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
# rpn anchor:
try:
if config.MODE_FPN:
multilevel_anchor_inputs = get_multilevel_rpn_anchor_input(im, boxes, is_crowd)
anchor_inputs = itertools.chain.from_iterable(multilevel_anchor_inputs)
else:
# anchor_labels, anchor_boxes
anchor_inputs = get_rpn_anchor_input(im, boxes, is_crowd)
assert len(anchor_inputs) == 2
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once("Input {} is filtered for training: {}".format(fname, str(e)), 'warn')
return None
ret = [im] + list(anchor_inputs) + [boxes, klass]
# TODO pad im when FPN
if add_mask:
# augmentation will modify the polys in-place
segmentation = copy.deepcopy(img['segmentation'])
segmentation = [segmentation[k] for k in range(len(segmentation)) if not is_crowd[k]]
assert len(segmentation) == len(boxes)
# Apply augmentation on polygon coordinates.
# And produce one image-sized binary mask per box.
masks = []
for polys in segmentation:
polys = [aug.augment_coords(p, params) for p in polys]
masks.append(segmentation_to_mask(polys, im.shape[0], im.shape[1]))
masks = np.asarray(masks, dtype='uint8') # values in {0, 1}
ret.append(masks)
# from viz import draw_annotation, draw_mask
# viz = draw_annotation(im, boxes, klass)
# for mask in masks:
# viz = draw_mask(viz, mask)
# tpviz.interactive_imshow(viz)
return ret
def preprocess(img):
fname, boxes, klass, is_crowd = img['file_name'], img['boxes'], img[
'class'], img['is_crowd']
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
# rpn anchor:
try:
fm_labels, fm_boxes = get_rpn_anchor_input(im, boxes, klass,
is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once(
"Input {} is invalid for training: {}".format(fname, str(e)),
'warn')
return None
ret = [im, fm_labels, fm_boxes, boxes, klass]
# masks
segmentation = img.get('segmentation', None)
if segmentation is not None:
segmentation = [
segmentation[k] for k in range(len(segmentation))
if not is_crowd[k]
]
assert len(segmentation) == len(boxes)
# one image-sized binary mask per box
masks = []
for polys in segmentation:
polys = [aug.augment_coords(p, params) for p in polys]
masks.append(
segmentation_to_mask(polys, im.shape[0], im.shape[1]))
masks = np.asarray(masks, dtype='uint8') # values in {0, 1}
ret.append(masks)
# from viz import draw_annotation, draw_mask
# viz = draw_annotation(im, boxes, klass)
# for mask in masks:
# viz = draw_mask(viz, mask)
# tpviz.interactive_imshow(viz)
return ret
def mapf(dp):
fname = dp[0]
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
dp[0] = im.astype('float32')
# assume floatbox as input
assert dp[1].dtype == np.float32
dp[1] = box_to_point8(dp[1])
dp.append(fname)
return dp
def preprocess(img):
fname, boxes, klass, is_crowd = img['file_name'], img['boxes'], img['class'], img['is_crowd']
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
# rpn anchor:
try:
fm_labels, fm_boxes = get_rpn_anchor_input(im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once("Input {} is filtered for training: {}".format(fname, str(e)), 'warn')
return None
ret = [im, fm_labels, fm_boxes, boxes, klass]
if add_mask:
# augmentation will modify the polys in-place
segmentation = copy.deepcopy(img['segmentation'])
segmentation = [segmentation[k] for k in range(len(segmentation)) if not is_crowd[k]]
assert len(segmentation) == len(boxes)
# Apply augmentation on polygon coordinates.
# And produce one image-sized binary mask per box.
masks = []
for polys in segmentation:
polys = [aug.augment_coords(p, params) for p in polys]
masks.append(segmentation_to_mask(polys, im.shape[0], im.shape[1]))
masks = np.asarray(masks, dtype='uint8') # values in {0, 1}
ret.append(masks)
# from viz import draw_annotation, draw_mask
# viz = draw_annotation(im, boxes, klass)
# for mask in masks:
# viz = draw_mask(viz, mask)
# tpviz.interactive_imshow(viz)
return ret
def predict_image_track(img, ref_img, ref_bbox, model_func):
"""
Run detection on one image, using the TF callable.
This function should handle the preprocessing internally.
Args:
img: an image
model_func: a callable from the TF model.
It takes image and returns (boxes, probs, labels, [masks])
Returns:
[DetectionResult]
"""
orig_shape = img.shape[:2]
resizer = CustomResize(cfg.PREPROC.TEST_SHORT_EDGE_SIZE,
cfg.PREPROC.MAX_SIZE)
resized_img = resizer.augment(img)
resized_ref_img, params = resizer.augment_return_params(ref_img)
ref_points = box_to_point8(ref_bbox[np.newaxis])
ref_points = resizer.augment_coords(ref_points, params)
resized_ref_boxes = point8_to_box(ref_points)
resized_ref_bbox = resized_ref_boxes[0]
scale = np.sqrt(resized_img.shape[0] * 1.0 / img.shape[0] *
resized_img.shape[1] / img.shape[1])
boxes, probs, labels, *masks = model_func(resized_img, resized_ref_img,
resized_ref_bbox)
boxes = boxes / scale
# boxes are already clipped inside the graph, but after the floating point scaling, this may not be true any more.
boxes = clip_boxes(boxes, orig_shape)
if masks:
# has mask
full_masks = [
_paste_mask(box, mask, orig_shape)
for box, mask in zip(boxes, masks[0])
]
masks = full_masks
else:
# fill with none
masks = [None] * len(boxes)
results = [
DetectionResult(*args) for args in zip(boxes, probs, labels, masks)
]
return results
def preprocess(img):
fname, boxes, klass, is_crowd = img['file_name'], img['boxes'], img[
'class'], img['is_crowd']
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
# rpn anchor:
try:
fm_labels, fm_boxes = get_rpn_anchor_input(im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once(
"Input {} is filtered for training: {}".format(fname, str(e)),
'warn')
return None
ret = [im, fm_labels, fm_boxes, boxes, klass]
# masks
if add_mask:
masks = img['masks']
masks = [np.dstack([m, m, m]) for m in masks]
masks = [aug.augment(m)[..., 0] for m in masks]
assert len(boxes) == np.asarray(masks).shape[0]
ret.append(masks)
# from viz import draw_annotation, draw_mask
# viz = draw_annotation(im, boxes, klass)
# for mask in masks:
# viz = draw_mask(viz, mask)
# tpviz.interactive_imshow(viz)
# input()
return ret
def _resize_image_together_with_boxes(self, img, *list_of_box_or_boxes):
resized_img, params = self._resizer.augment_return_params(img)
res_boxes = []
for box_or_boxes in list_of_box_or_boxes:
expand = len(box_or_boxes.shape) == 1
if expand:
boxes = box_or_boxes[np.newaxis]
else:
boxes = box_or_boxes
points = box_to_point8(boxes)
points = self._resizer.augment_coords(points, params)
resized_boxes = point8_to_box(points)
if expand:
resized_boxes = np.squeeze(resized_boxes, axis=0)
res_boxes.append(resized_boxes)
if len(res_boxes) == 1:
res_boxes = res_boxes[0]
return resized_img, res_boxes
def preprocess(img):
fname, boxes, re_id_class = img['file_name'], img['boxes'], img[
're_id_class']
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
ret = [im, boxes, re_id_class]
return ret
def preprocess(img):
fname, boxes, klass, is_crowd, re_id_class = img['file_name'], img['boxes'], \
img['class'], img['is_crowd'], img['re_id_class']
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
orig_shape = im.shape[:2]
orig_im = np.copy(im)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
# rpn anchor:
try:
# anchor_labels, anchor_boxes
anchor_inputs = get_rpn_anchor_input(im, boxes, is_crowd)
assert len(anchor_inputs) == 2
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once(
"Input {} is filtered for training: {}".format(fname, str(e)),
'warn')
return None
ret = [im] + list(anchor_inputs) + [
boxes, klass, re_id_class, orig_shape, orig_im
]
return ret
def __call__(self, roidb):
fname, boxes, klass, is_crowd = roidb["file_name"], roidb["boxes"], roidb["class"], roidb["is_crowd"]
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype("float32")
height, width = im.shape[:2]
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
if not self.cfg.DATA.ABSOLUTE_COORD:
boxes[:, 0::2] *= width
boxes[:, 1::2] *= height
# augmentation:
im, params = self.aug.augment_return_params(im)
points = box_to_point8(boxes)
points = self.aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
ret = {"image": im}
# Add rpn data to dataflow:
try:
if self.cfg.MODE_FPN:
multilevel_anchor_inputs = self.get_multilevel_rpn_anchor_input(im, boxes, is_crowd)
for i, (anchor_labels, anchor_boxes) in enumerate(multilevel_anchor_inputs):
ret["anchor_labels_lvl{}".format(i + 2)] = anchor_labels
ret["anchor_boxes_lvl{}".format(i + 2)] = anchor_boxes
else:
ret["anchor_labels"], ret["anchor_boxes"] = self.get_rpn_anchor_input(im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
ret["gt_boxes"] = boxes
ret["gt_labels"] = klass
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once("Input {} is filtered for training: {}".format(fname, str(e)), "warn")
return None
if self.cfg.MODE_MASK:
# augmentation will modify the polys in-place
segmentation = copy.deepcopy(roidb["segmentation"])
segmentation = [segmentation[k] for k in range(len(segmentation)) if not is_crowd[k]]
assert len(segmentation) == len(boxes)
# Apply augmentation on polygon coordinates.
# And produce one image-sized binary mask per box.
masks = []
width_height = np.asarray([width, height], dtype=np.float32)
gt_mask_width = int(np.ceil(im.shape[1] / 8.0) * 8) # pad to 8 in order to pack mask into bits
for polys in segmentation:
if not self.cfg.DATA.ABSOLUTE_COORD:
polys = [p * width_height for p in polys]
polys = [self.aug.augment_coords(p, params) for p in polys]
masks.append(segmentation_to_mask(polys, im.shape[0], gt_mask_width))
masks = np.asarray(masks, dtype='uint8') # values in {0, 1}
masks = np.packbits(masks, axis=-1)
ret['gt_masks_packed'] = masks
# from viz import draw_annotation, draw_mask
# viz = draw_annotation(im, boxes, klass)
# for mask in masks:
# viz = draw_mask(viz, mask)
# tpviz.interactive_imshow(viz)
return ret
def preprocess(roidb_batch):
datapoint_list = []
for roidb in roidb_batch:
fname, boxes, klass, is_crowd = roidb['file_name'], roidb['boxes'], roidb['class'], roidb['is_crowd']
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
ret = {'images': im}
# rpn anchor:
try:
if cfg.MODE_FPN:
multilevel_anchor_inputs = get_multilevel_rpn_anchor_input(im, boxes, is_crowd)
for i, (anchor_labels, anchor_boxes) in enumerate(multilevel_anchor_inputs):
ret['anchor_labels_lvl{}'.format(i + 2)] = anchor_labels
ret['anchor_boxes_lvl{}'.format(i + 2)] = anchor_boxes
else:
raise NotImplementedError("[armand] Batch mode only available for FPN")
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
ret['gt_boxes'] = boxes
ret['gt_labels'] = klass
ret['filename'] = fname
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once("Input {} is filtered for training: {}".format(fname, str(e)), 'warn')
return None
if cfg.MODE_MASK:
# augmentation will modify the polys in-place
segmentation = copy.deepcopy(roidb['segmentation'])
segmentation = [segmentation[k] for k in range(len(segmentation)) if not is_crowd[k]]
assert len(segmentation) == len(boxes)
# Apply augmentation on polygon coordinates.
# And produce one image-sized binary mask per box.
masks = []
for polys in segmentation:
polys = [aug.augment_coords(p, params) for p in polys]
masks.append(segmentation_to_mask(polys, im.shape[0], im.shape[1]))
masks = np.asarray(masks, dtype='uint8') # values in {0, 1}
ret['gt_masks'] = masks
datapoint_list.append(ret)
#################################################################################################################
# Batchify the output
#################################################################################################################
# Now we need to batch the various fields
# Easily stackable:
# - anchor_labels_lvl2
# - anchor_boxes_lvl2
# - anchor_labels_lvl3
# - anchor_boxes_lvl3
# - anchor_labels_lvl4
# - anchor_boxes_lvl4
# - anchor_labels_lvl5
# - anchor_boxes_lvl5
# - anchor_labels_lvl6
# - anchor_boxes_lvl6
batched_datapoint = {}
for stackable_field in ["anchor_labels_lvl2",
"anchor_boxes_lvl2",
"anchor_labels_lvl3",
"anchor_boxes_lvl3",
"anchor_labels_lvl4",
"anchor_boxes_lvl4",
"anchor_labels_lvl5",
"anchor_boxes_lvl5",
"anchor_labels_lvl6",
"anchor_boxes_lvl6"]:
batched_datapoint[stackable_field] = np.stack([d[stackable_field] for d in datapoint_list])
# Require padding and original dimension storage
# - image (HxWx3)
# - gt_boxes (?x4)
# - gt_labels (?)
# - gt_masks (?xHxW)
"""
Find the minimum container size for images (maxW x maxH)
Find the maximum number of ground truth boxes
For each image, save original dimension and pad
"""
if cfg.PREPROC.PREDEFINED_PADDING:
padding_shapes = [get_padding_shape(*(d["images"].shape[:2])) for d in datapoint_list]
max_height = max([shp[0] for shp in padding_shapes])
max_width = max([shp[1] for shp in padding_shapes])
else:
image_dims = [d["images"].shape for d in datapoint_list]
heights = [dim[0] for dim in image_dims]
widths = [dim[1] for dim in image_dims]
max_height = max(heights)
max_width = max(widths)
# image
padded_images = []
original_image_dims = []
for datapoint in datapoint_list:
image = datapoint["images"]
original_image_dims.append(image.shape)
h_padding = max_height - image.shape[0]
w_padding = max_width - image.shape[1]
padded_image = np.pad(image,
[[0, h_padding],
[0, w_padding],
[0, 0]],
'constant')
padded_images.append(padded_image)
batched_datapoint["images"] = np.stack(padded_images)
#print(batched_datapoint["images"].shape)
batched_datapoint["orig_image_dims"] = np.stack(original_image_dims)
# gt_boxes and gt_labels
max_num_gts = max([d["gt_labels"].size for d in datapoint_list])
gt_counts = []
padded_gt_labels = []
padded_gt_boxes = []
padded_gt_masks = []
for datapoint in datapoint_list:
gt_count_for_image = datapoint["gt_labels"].size
gt_counts.append(gt_count_for_image)
gt_padding = max_num_gts - gt_count_for_image
padded_gt_labels_for_img = np.pad(datapoint["gt_labels"], [0, gt_padding], 'constant', constant_values=-1)
padded_gt_labels.append(padded_gt_labels_for_img)
padded_gt_boxes_for_img = np.pad(datapoint["gt_boxes"],
[[0, gt_padding],
[0,0]],
'constant')
padded_gt_boxes.append(padded_gt_boxes_for_img)
h_padding = max_height - datapoint["images"].shape[0]
w_padding = max_width - datapoint["images"].shape[1]
if cfg.MODE_MASK:
padded_gt_masks_for_img = np.pad(datapoint["gt_masks"],
[[0, gt_padding],
[0, h_padding],
[0, w_padding]],
'constant')
padded_gt_masks.append(padded_gt_masks_for_img)
batched_datapoint["orig_gt_counts"] = np.stack(gt_counts)
batched_datapoint["gt_labels"] = np.stack(padded_gt_labels)
batched_datapoint["gt_boxes"] = np.stack(padded_gt_boxes)
batched_datapoint["filenames"] = [d["filename"] for d in datapoint_list]
if cfg.MODE_MASK:
batched_datapoint["gt_masks"] = np.stack(padded_gt_masks)
return batched_datapoint
def preprocess(roidb):
fname, boxes, klass, is_crowd = roidb['file_name'], roidb[
'boxes'], roidb['class'], roidb['is_crowd']
boxes = np.copy(boxes)
im = imread(fname)
assert im is not None, fname
im = np.expand_dims(im, axis=2)
im = np.repeat(im, 3, axis=2)
im = im.astype('float32')
#height, width = im.shape[:2]
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
if not cfg.DATA.ABSOLUTE_COORD:
boxes[:, 0::2] *= width
boxes[:, 1::2] *= height
#source_image = Image.fromarray(im.astype('uint8'))
#imsave('./input_image1', im[:,:,1].astype(np.float32), imagej=True)
"""
draw = ImageDraw.Draw(source_image)
for i, bbox in enumerate(boxes):
# tmp_x = bbox[2] - bbox[0]
# tmp_y = bbox[3] - bbox[1]
# draw.rectangle((bbox[0], bbox[1], tmp_x, tmp_y), outline='red')
draw.rectangle((bbox[0], bbox[1], bbox[2], bbox[3]), outline='red')
#draw.text((bbox[0] + 5, bbox[1] + 5), str(klass_tmp[i]))
source_image.save('./input_image1', "JPEG")
"""
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
klass_tmp = np.copy(klass)
#print(klass)
#imsave('./input_image2', im[:,:,1].astype(np.float32), imagej=True)
"""
source_image = Image.fromarray(im.astype('uint8'))
draw = ImageDraw.Draw(source_image)
for i, bbox in enumerate(boxes):
# tmp_x = bbox[2] - bbox[0]
# tmp_y = bbox[3] - bbox[1]
# draw.rectangle((bbox[0], bbox[1], tmp_x, tmp_y), outline='red')
draw.rectangle((bbox[0], bbox[1], bbox[2], bbox[3]), outline='red')
#draw.text((bbox[0]+5, bbox[1]+5), str(klass_tmp[i]))
source_image.save('./input_image2', "JPEG")
"""
ret = {'image': im}
# rpn anchor:
try:
if cfg.MODE_FPN:
multilevel_anchor_inputs = get_multilevel_rpn_anchor_input(
im, boxes, is_crowd)
for i, (anchor_labels,
anchor_boxes) in enumerate(multilevel_anchor_inputs):
ret['anchor_labels_lvl{}'.format(i + 2)] = anchor_labels
ret['anchor_boxes_lvl{}'.format(i + 2)] = anchor_boxes
else:
# anchor_labels, anchor_boxes
ret['anchor_labels'], ret[
'anchor_boxes'] = get_rpn_anchor_input(
im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
ret['gt_boxes'] = boxes
ret['gt_labels'] = klass
if not len(boxes):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once(
"Input {} is filtered for training: {}".format(fname, str(e)),
'warn')
return None
if cfg.MODE_MASK:
# augmentation will modify the polys in-place
segmentation = copy.deepcopy(roidb['segmentation'])
segmentation = [
segmentation[k] for k in range(len(segmentation))
if not is_crowd[k]
]
assert len(segmentation) == len(boxes)
# Apply augmentation on polygon coordinates.
# And produce one image-sized binary mask per box.
masks = []
width_height = np.asarray([width, height], dtype=np.float32)
for polys in segmentation:
if not cfg.DATA.ABSOLUTE_COORD:
polys = [p * width_height for p in polys]
polys = [aug.augment_coords(p, params) for p in polys]
masks.append(
segmentation_to_mask(polys, im.shape[0], im.shape[1]))
masks = np.asarray(masks, dtype='uint8') # values in {0, 1}
ret['gt_masks'] = masks
# from viz import draw_annotation, draw_mask
# viz = draw_annotation(im, boxes, klass)
# for mask in masks:
# viz = draw_mask(viz, mask)
# tpviz.interactive_imshow(viz)
return ret
def preprocess(img):
fname, boxes, klass, is_crowd = img['file_name'], img['boxes'], img[
'class'], img['is_crowd']
img_name = fname.split('/')[-1]
img_id = int(img_name[3:-4])
# pretrain rpn for negtive chip extraction
proposals = proposal_pickle['boxes'][proposal_pickle['ids'].index(
img_id)]
proposals[2:4] += proposals[0:2] # from [x,y,w,h] to [x1,y1,x2,y2]
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype('float32')
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return floating point boxes!"
# augmentation:
im, params = aug.augment_return_params(im)
points = box_to_point8(boxes)
points = aug.augment_coords(points, params)
boxes = point8_to_box(points)
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
chip_generator = Im2Chip(im,
boxes,
klass,
proposals,
cfg.SNIPER.SCALES,
cfg.SNIPER.VALID_RANGES,
is_crowd=is_crowd,
chip_size=cfg.SNIPER.CHIP_SIZE,
chip_stride=cfg.SNIPER.CHIP_STRIDE)
im, boxes, klass, scale_indices, is_crowd = chip_generator.genChipMultiScale(
)
rets = []
for i in range(len(im)):
try:
if len(boxes[i]) == 0:
continue
# anchor_labels, anchor_boxes
gt_invalid = []
maxbox = cfg.SNIPER.VALID_RANGES[scale_indices[i]][0]
minbox = cfg.SNIPER.VALID_RANGES[scale_indices[i]][1]
maxbox = sys.maxsize if maxbox == -1 else maxbox
minbox = 0 if minbox == -1 else minbox
for box in boxes[i]:
w = box[2] - box[0]
h = box[3] - box[1]
if w >= maxbox or h >= maxbox or (w < minbox
and h < minbox):
gt_invalid.append(box)
anchor_inputs = get_sniper_rpn_anchor_input(
im[i], boxes[i], is_crowd[i], gt_invalid)
assert len(anchor_inputs) == 2
boxes[i] = boxes[i][is_crowd[i] ==
0] # skip crowd boxes in training target
klass[i] = klass[i][is_crowd[i] == 0]
if not len(boxes[i]):
raise MalformedData("No valid gt_boxes!")
except MalformedData as e:
log_once(
"Input {} is filtered for training: {}".format(
fname, str(e)), 'warn')
ret = None
continue
# ret = [im[i]] + list(anchor_inputs) + [boxes[i], klass[i]
# ] + [scale_indices[i]*len(boxes[i])]
ret = [im[i]] + list(anchor_inputs) + [boxes[i], klass[i]]
rets.append(ret)
return rets
