def _crop(image, boxes, labels):
height, width, _ = image.shape
if len(boxes)== 0:
return image, boxes, labels
while True:
mode = random.choice((
None,
(0.1, None),
(0.3, None),
(0.5, None),
(0.7, None),
(0.9, None),
(None, None),
))
if mode is None:
return image, boxes, labels
min_iou, max_iou = mode
if min_iou is None:
min_iou = float('-inf')
if max_iou is None:
max_iou = float('inf')
for _ in range(50):
scale = random.uniform(0.3,1.)
min_ratio = max(0.5, scale*scale)
max_ratio = min(2, 1. / scale / scale)
ratio = math.sqrt(random.uniform(min_ratio, max_ratio))
w = int(scale * ratio * width)
h = int((scale / ratio) * height)
l = random.randrange(width - w)
t = random.randrange(height - h)
roi = np.array((l, t, l + w, t + h))
iou = matrix_iou(boxes, roi[np.newaxis])
if not (min_iou <= iou.min() and iou.max() <= max_iou):
continue
image_t = image[roi[1]:roi[3], roi[0]:roi[2]]
centers = (boxes[:, :2] + boxes[:, 2:]) / 2
mask = np.logical_and(roi[:2] < centers, centers < roi[2:]) \
.all(axis=1)
boxes_t = boxes[mask].copy()
labels_t = labels[mask].copy()
if len(boxes_t) == 0:
continue
boxes_t[:, :2] = np.maximum(boxes_t[:, :2], roi[:2])
boxes_t[:, :2] -= roi[:2]
boxes_t[:, 2:] = np.minimum(boxes_t[:, 2:], roi[2:])
boxes_t[:, 2:] -= roi[:2]
return image_t, boxes_t,labels_t
def _crop(image, boxes, labels):
height, width, _ = image.shape
if random.uniform(0., 1.) > 0.15 or len(boxes) == 0:
return image, boxes, labels
while True:
mode = random.choice((
# (min_iou, max_iou, min_object_covered)
(0.0, None, 0.0),
(0.1, None, 0.1),
(0.3, None, 0.3),
(0.5, None, 0.5),
(0.7, None, 0.7),
(0.9, None, 0.9),
(1.0, None, 1.0),
))
min_iou, max_iou = mode[:2]
if min_iou is None:
min_iou = float('-inf')
if max_iou is None:
max_iou = float('inf')
for _ in range(100):
scale = random.uniform(0.1, 1.)
min_ratio = max(0.5, scale * scale)
max_ratio = min(2, 1. / scale / scale)
ratio = math.sqrt(random.uniform(min_ratio, max_ratio))
w = int(scale * ratio * width)
h = int((scale / ratio) * height)
"""
min_ratio = max(0.5, float(width) / height * scale)
max_ratio = min(2., float(width) / height / scale)
ratio = random.uniform(min_ratio, max_ratio) # ratio = new_w/new_h
w = int(math.sqrt(scale * ratio * width * height))
h = int(math.sqrt(scale / ratio * width * height))
"""
l = random.randrange(width - w)
t = random.randrange(height - h)
roi = np.array((l, t, l + w, t + h))
iou = matrix_iou(boxes, roi[np.newaxis])
if not (min_iou <= iou.min() and iou.max() <= max_iou):
continue
image_t = image[roi[1]:roi[3], roi[0]:roi[2]]
centers = (boxes[:, :2] + boxes[:, 2:]) / 2
mask = np.logical_and(roi[:2] < centers, centers < roi[2:]) \
.all(axis=1)
boxes_t = boxes[mask].copy()
labels_t = labels[mask].copy()
if float(len(boxes_t)) / len(boxes) >= mode[2]:
continue
boxes_t[:, :2] = np.maximum(boxes_t[:, :2], roi[:2])
boxes_t[:, :2] -= roi[:2]
boxes_t[:, 2:] = np.minimum(boxes_t[:, 2:], roi[2:])
boxes_t[:, 2:] -= roi[:2]
return image_t, boxes_t, labels_t
# after max_attempts failures, return the entire image
return image, boxes, labels
def _crop(self, image, boxes, labels):
height, width, _ = image.shape
min_cropped_ratio = 0.4 if _FOR_PMI_UKRAINE else 0.70
if len(boxes) == 0 or (len(boxes) == 1 and labels[0] == 0):
scale = random.uniform(0.70, 1.)
#just keep aspect ratio
#ratio = 1.0
scale = random.uniform(min_cropped_ratio, 1.)
min_ratio = max(0.8, scale * scale)
max_ratio = min(1 / 0.8, 1. / scale / scale)
ratio = math.sqrt(random.uniform(min_ratio, max_ratio))
w = int(scale * ratio * width)
h = int((scale / ratio) * height)
l = random.randrange(width - w)
t = random.randrange(height - h)
roi = np.array((l, t, l + w, t + h))
image_t = image[roi[1]:roi[3], roi[0]:roi[2]]
return image_t, boxes, labels
area = np.prod(boxes[:, 2:] - boxes[:, :2], axis=1) / (height * width)
big_sku = np.mean(area) >= 0.05
if big_sku:
return image, boxes, labels
while True:
mode = random.choice((
None,
(0.001, 0.05), #0.025*0.025=0.000625
(0.002, 0.10),
(0.005, 0.10),
(0.01, 0.1),
(0.05, 0.25),
(0.1, 0.30),
(0.25, 0.5),
#(0.5, None),
#(0.7, None),
#(0.9, None),
(None, None),
))
if mode is None:
return image, boxes, labels
min_iou, max_iou = mode
if min_iou is None:
min_iou = float('-inf')
if max_iou is None:
max_iou = float('inf')
for _ in range(50):
#scale = random.uniform(0.50, 1.)
#it is very strange, pmi ukraine has stock counter function,
#the sku in such image is quite big, so need to crop out a small portion
#and resize it to [800,600] to make a fake big sku in training stage.
scale = random.uniform(min_cropped_ratio, 1.)
min_ratio = max(0.85, scale * scale)
max_ratio = min(1 / 0.85, 1. / scale / scale)
ratio = math.sqrt(random.uniform(min_ratio, max_ratio))
#just keep aspect ratio
#ratio = 1.0
w = int(scale * ratio * width)
h = int((scale / ratio) * height)
l = random.randrange(width - w)
t = random.randrange(height - h)
roi = np.array((l, t, l + w, t + h))
iou = matrix_iou(boxes, roi[np.newaxis])
if not (min_iou <= iou.min() and iou.max() <= max_iou):
continue
image_t = image[roi[1]:roi[3], roi[0]:roi[2]]
#centers = (boxes[:, :2] + boxes[:, 2:]) / 2
#mask = np.logical_and(roi[:2] < centers, centers < roi[2:]).all(axis=1)
mask = (iou > (1 / 2400)).squeeze(1)
boxes_t = boxes[mask].copy()
labels_t = labels[mask].copy()
if len(boxes_t) == 0:
continue
old_boxes_t = boxes_t.copy()
boxes_t[:, :2] = np.maximum(boxes_t[:, :2], roi[:2])
boxes_t[:, :2] -= roi[:2]
boxes_t[:, 2:] = np.minimum(boxes_t[:, 2:], roi[2:])
boxes_t[:, 2:] -= roi[:2]
#
new_area = (boxes_t[:, 2] - boxes_t[:, 0]) * (boxes_t[:, 3] -
boxes_t[:, 1])
old_area = (old_boxes_t[:, 2] - old_boxes_t[:, 0]) * (
old_boxes_t[:, 3] - old_boxes_t[:, 1])
iou = new_area / old_area
mask = iou <= 0.65
bad_mask = mask
#print(self.ambigous_skus)
#if True:
if len(self.ambigous_skus) > 0:
mask_ambigous_skus_idx = [
sku in self.ambigous_skus for sku in labels_t
]
#mask2 = 2<=labels_t
mask_ambigous_skus_crop_ratio = iou < (
1 - self.ambigous_skus_crop_ratio)
mask_ambigous_skus = mask_ambigous_skus_idx & mask_ambigous_skus_crop_ratio
bad_mask = mask | mask_ambigous_skus
pp_boxes = boxes_t[mask_ambigous_skus]
bad_boxes_t = boxes_t[bad_mask]
if len(pp_boxes) > 1000:
print(self.ambigous_skus)
print(self.ambigous_skus_crop_ratio)
print(iou)
print(labels_t)
print(mask_ambigous_skus)
print(bad_mask)
bad_boxes_t = boxes_t[bad_mask]
for box in bad_boxes_t:
#print("black out the box because iou <0.7")
image_t[int(box[1]):int(box[3]),
int(box[0]):int(box[2])] = random.randint(0, 255)
boxes_t = boxes_t[~bad_mask]
labels_t = labels_t[~bad_mask]
if len(boxes_t) == 0:
targets = np.zeros((1, 5))
boxes_t = targets[:, :-1].copy()
labels_t = targets[:, -1].copy()
return image_t, boxes_t, labels_t