def preprocess_func(image, image_meta, boxes=None):
"""
Performs preprocessing on images
"""
rgb_mean = (np.array([93.877, 98.801, 95.923], dtype=np.float32).reshape(1, 1, 3))
rgb_std = (np.array([78.782, 80.130, 81.200], dtype=np.float32).reshape(1, 1, 3))
if boxes is not None:
# [x, y, w, h] -> 0, 2 -> x and width
# a, min max -> boxes x1 and x2 coordinations, min is 0 and max is the orig_size of input
boxes[:, [0, 2]] = np.clip(boxes[:, [0, 2]], 0., image_meta['orig_size'][1] - 1.) # min max out -> deals with the width
boxes[:, [1, 3]] = np.clip(boxes[:, [1, 3]], 0., image_meta['orig_size'][0] - 1.) # deals with the height
drift_prob = 0.
flip_prob = 0.
#image, image_meta = whiten(image, image_meta, mean=rgb_mean, std=rgb_std)
image, image_meta, boxes = drift(image, image_meta, prob=drift_prob, boxes=boxes)
image,image_meta, boxes = flip(image, image_meta, prob=flip_prob, boxes=boxes)
# if args.forbid_resize:
# image, image_meta, boxes = crop_or_pad(image, image_meta, args.input_size, boxes=boxes)
# else:
# image, image_meta, boxes = resize(image, image_meta, (384, 1248), boxes=boxes)
return image, image_meta, boxes
def preprocess(self,
input_size,
image,
image_meta,
boxes=None,
drift_prob,
flip_prob,
forbid_resize=False):
"""
Performs preprocessing on images
"""
if boxes is not None:
# [x, y, w, h] -> 0, 2 -> x and width
boxes[:,
[0, 2]] = np.clip(boxes[:, [0, 2]], 0.,
image_meta['orig_size'][1] -
1.) # min max out -> deals with the width
boxes[:, [1, 3]] = np.clip(boxes[:, [1, 3]], 0.,
image_meta['orig_size'][0] -
1.) # deals with the height
drift_prob = drift_prob if self.phase == 'train' else 0.
flip_prob = flip_prob if self.phase == 'train' else 0.
image, image_meta = whiten(image,
image_meta,
mean=self.rgb_mean,
std=self.rgb_std)
image, image_meta, boxes = drift(image,
image_meta,
prob=drift_prob,
boxes=boxes)
image, image_meta, boxes = flip(image,
image_meta,
prob=flip_prob,
boxes=boxes)
if forbid_resize == True:
image, image_meta, boxes = crop_or_pad(image,
image_meta,
input_size,
boxes=boxes)
else:
image, image_meta, boxes = resize(image,
image_meta,
input_size,
boxes=boxes)
return image, image_meta, boxes
def preprocess(self, image, image_meta, boxes=None):
"""
Performs preprocessing on images
"""
if boxes is not None:
# [x, y, w, h] -> 0, 2 -> x and width
# a, min max -> boxes x1 and x2 coordinations, min is 0 and max is the orig_size of input
boxes[:,
[0, 2]] = np.clip(boxes[:, [0, 2]], 0.,
image_meta['orig_size'][1] -
1.) # min max out -> deals with the width
boxes[:, [1, 3]] = np.clip(boxes[:, [1, 3]], 0.,
image_meta['orig_size'][0] -
1.) # deals with the height
drift_prob = self.args.drift_prob if self.phase == 'train' else 0.
flip_prob = self.args.flip_prob if self.phase == 'train' else 0.
image, image_meta = whiten(image,
image_meta,
mean=self.rgb_mean,
std=self.rgb_std)
image, image_meta, boxes = drift(image,
image_meta,
prob=drift_prob,
boxes=boxes)
image, image_meta, boxes = flip(image,
image_meta,
prob=flip_prob,
boxes=boxes)
if self.args.forbid_resize:
image, image_meta, boxes = crop_or_pad(image,
image_metea,
self.input_size,
boxes=boxes)
else:
image, image_meta, boxes = resize(image,
image_meta,
self.input_size,
boxes=boxes)
return image, image_meta, boxes