Spaces:
Running
Running
File size: 9,682 Bytes
29f689c 695a4a4 29f689c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
import numpy as np
import cv2
import torch
from shapely.geometry import Polygon
import pyclipper
"""
This code is refered from:
https://github.com/WenmuZhou/DBNet.pytorch/blob/master/post_processing/seg_detector_representer.py
"""
class DBPostProcess(object):
"""
The post process for Differentiable Binarization (DB).
"""
def __init__(
self,
thresh=0.3,
box_thresh=0.7,
max_candidates=1000,
unclip_ratio=2.0,
use_dilation=False,
score_mode='fast',
box_type='quad',
**kwargs,
):
self.thresh = thresh
self.box_thresh = box_thresh
self.max_candidates = max_candidates
self.unclip_ratio = unclip_ratio
self.min_size = 3
self.score_mode = score_mode
self.box_type = box_type
assert score_mode in [
'slow',
'fast',
], 'Score mode must be in [slow, fast] but got: {}'.format(score_mode)
self.dilation_kernel = None if not use_dilation else np.array([[1, 1],
[1, 1]])
def polygons_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
"""
_bitmap: single map with shape (1, H, W),
whose values are binarized as {0, 1}
"""
bitmap = _bitmap
height, width = bitmap.shape
boxes = []
scores = []
contours, _ = cv2.findContours((bitmap * 255).astype(np.uint8),
cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
for contour in contours[:self.max_candidates]:
epsilon = 0.002 * cv2.arcLength(contour, True)
approx = cv2.approxPolyDP(contour, epsilon, True)
points = approx.reshape((-1, 2))
if points.shape[0] < 4:
continue
score = self.box_score_fast(pred, points.reshape(-1, 2))
if self.box_thresh > score:
continue
if points.shape[0] > 2:
box = self.unclip(points, self.unclip_ratio)
if len(box) > 1:
continue
else:
continue
box = np.array(box).reshape(-1, 2)
if len(box) == 0:
continue
_, sside = self.get_mini_boxes(box.reshape((-1, 1, 2)))
if sside < self.min_size + 2:
continue
box = np.array(box)
box[:, 0] = np.clip(np.round(box[:, 0] / width * dest_width), 0,
dest_width)
box[:, 1] = np.clip(np.round(box[:, 1] / height * dest_height), 0,
dest_height)
boxes.append(box.tolist())
scores.append(score)
return boxes, scores
def boxes_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
"""
_bitmap: single map with shape (1, H, W),
whose values are binarized as {0, 1}
"""
bitmap = _bitmap
height, width = bitmap.shape
outs = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST,
cv2.CHAIN_APPROX_SIMPLE)
if len(outs) == 3:
img, contours, _ = outs[0], outs[1], outs[2]
elif len(outs) == 2:
contours, _ = outs[0], outs[1]
num_contours = min(len(contours), self.max_candidates)
boxes = []
scores = []
for index in range(num_contours):
contour = contours[index]
points, sside = self.get_mini_boxes(contour)
if sside < self.min_size:
continue
points = np.array(points)
if self.score_mode == 'fast':
score = self.box_score_fast(pred, points.reshape(-1, 2))
else:
score = self.box_score_slow(pred, contour)
if self.box_thresh > score:
continue
box = self.unclip(points, self.unclip_ratio)
if len(box) > 1:
continue
box = np.array(box).reshape(-1, 1, 2)
box, sside = self.get_mini_boxes(box)
if sside < self.min_size + 2:
continue
box = np.array(box)
box[:, 0] = np.clip(np.round(box[:, 0] / width * dest_width), 0,
dest_width)
box[:, 1] = np.clip(np.round(box[:, 1] / height * dest_height), 0,
dest_height)
boxes.append(box.astype('int32'))
scores.append(score)
return np.array(boxes, dtype='int32'), scores
def unclip(self, box, unclip_ratio):
poly = Polygon(box)
distance = poly.area * unclip_ratio / poly.length
offset = pyclipper.PyclipperOffset()
offset.AddPath(box, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
expanded = offset.Execute(distance)
return expanded
def get_mini_boxes(self, contour):
bounding_box = cv2.minAreaRect(contour)
points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])
index_1, index_2, index_3, index_4 = 0, 1, 2, 3
if points[1][1] > points[0][1]:
index_1 = 0
index_4 = 1
else:
index_1 = 1
index_4 = 0
if points[3][1] > points[2][1]:
index_2 = 2
index_3 = 3
else:
index_2 = 3
index_3 = 2
box = [
points[index_1], points[index_2], points[index_3], points[index_4]
]
return box, min(bounding_box[1])
def box_score_fast(self, bitmap, _box):
"""
box_score_fast: use bbox mean score as the mean score
"""
h, w = bitmap.shape[:2]
box = _box.copy()
xmin = np.clip(np.floor(box[:, 0].min()).astype('int32'), 0, w - 1)
xmax = np.clip(np.ceil(box[:, 0].max()).astype('int32'), 0, w - 1)
ymin = np.clip(np.floor(box[:, 1].min()).astype('int32'), 0, h - 1)
ymax = np.clip(np.ceil(box[:, 1].max()).astype('int32'), 0, h - 1)
mask = np.zeros((ymax - ymin + 1, xmax - xmin + 1), dtype=np.uint8)
box[:, 0] = box[:, 0] - xmin
box[:, 1] = box[:, 1] - ymin
cv2.fillPoly(mask, box.reshape(1, -1, 2).astype('int32'), 1)
return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0]
def box_score_slow(self, bitmap, contour):
"""
box_score_slow: use polyon mean score as the mean score
"""
h, w = bitmap.shape[:2]
contour = contour.copy()
contour = np.reshape(contour, (-1, 2))
xmin = np.clip(np.min(contour[:, 0]), 0, w - 1)
xmax = np.clip(np.max(contour[:, 0]), 0, w - 1)
ymin = np.clip(np.min(contour[:, 1]), 0, h - 1)
ymax = np.clip(np.max(contour[:, 1]), 0, h - 1)
mask = np.zeros((ymax - ymin + 1, xmax - xmin + 1), dtype=np.uint8)
contour[:, 0] = contour[:, 0] - xmin
contour[:, 1] = contour[:, 1] - ymin
cv2.fillPoly(mask, contour.reshape(1, -1, 2).astype('int32'), 1)
return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0]
def __call__(self, outs_dict, shape_list, **kwargs):
self.thresh= kwargs.get('thresh', self.thresh)
self.box_thresh = kwargs.get('box_thresh', self.box_thresh)
self.unclip_ratio = kwargs.get('unclip_ratio', self.unclip_ratio)
self.box_type = kwargs.get('box_type', self.box_type)
self.score_mode = kwargs.get('score_mode', self.score_mode)
pred = outs_dict['maps']
if isinstance(pred, torch.Tensor):
pred = pred.detach().cpu().numpy()
pred = pred[:, 0, :, :]
segmentation = pred > self.thresh
boxes_batch = []
for batch_index in range(pred.shape[0]):
src_h, src_w, ratio_h, ratio_w = shape_list[batch_index]
if self.dilation_kernel is not None:
mask = cv2.dilate(
np.array(segmentation[batch_index]).astype(np.uint8),
self.dilation_kernel,
)
else:
mask = segmentation[batch_index]
if self.box_type == 'poly':
boxes, scores = self.polygons_from_bitmap(
pred[batch_index], mask, src_w, src_h)
elif self.box_type == 'quad':
boxes, scores = self.boxes_from_bitmap(pred[batch_index], mask,
src_w, src_h)
else:
raise ValueError(
"box_type can only be one of ['quad', 'poly']")
boxes_batch.append({'points': boxes})
return boxes_batch
class DistillationDBPostProcess(object):
def __init__(
self,
model_name=['student'],
key=None,
thresh=0.3,
box_thresh=0.6,
max_candidates=1000,
unclip_ratio=1.5,
use_dilation=False,
score_mode='fast',
box_type='quad',
**kwargs,
):
self.model_name = model_name
self.key = key
self.post_process = DBPostProcess(
thresh=thresh,
box_thresh=box_thresh,
max_candidates=max_candidates,
unclip_ratio=unclip_ratio,
use_dilation=use_dilation,
score_mode=score_mode,
box_type=box_type,
)
def __call__(self, predicts, shape_list):
results = {}
for k in self.model_name:
results[k] = self.post_process(predicts[k], shape_list=shape_list)
return results
|