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 = roidb['img']
x1, y1, w, h = np.split(roidb['bbox'], 4, axis=1)
boxes = np.concatenate([x1, y1, x1 + w, y1 + h], axis=1)
klass = np.ones(len(roidb['bbox']), dtype=np.int32)
male = roidb['male']
longhair = roidb['longhair']
sunglass = roidb['sunglass']
hat = roidb['hat']
tshirt = roidb['tshirt']
longsleeve = roidb['longsleeve']
formal = roidb['formal']
shorts = roidb['shorts']
jeans = roidb['jeans']
longpants = roidb['longpants']
skirt = roidb['skirt']
facemask = roidb['facemask']
logo = roidb['logo']
stripe = roidb['stripe']
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:
# anchor_labels, anchor_boxes
ret['anchor_labels'], ret['anchor_boxes'] = get_rpn_anchor_input(
im, boxes, np.zeros(len(boxes), dtype=int))
ret['gt_boxes'] = boxes
ret['gt_labels'] = klass
ret['male'] = male
ret['longhair'] = longhair
ret['sunglass'] = sunglass
ret['hat'] = hat
ret['tshirt'] = tshirt
ret['longsleeve'] = longsleeve
ret['formal'] = formal
ret['shorts'] = shorts
ret['jeans'] = jeans
ret['longpants'] = longpants
ret['skirt'] = skirt
ret['facemask'] = facemask
ret['logo'] = logo
ret['stripe'] = stripe
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