-
Notifications
You must be signed in to change notification settings - Fork 2.3k
Open
Description
完整覆盖本地的 dbnet/decode.py 文件的所有内容即可修复
dbnet/decode.py
import cv2
import numpy as np
import pyclipper
from shapely.geometry import Polygon
class SegDetectorRepresenter:
def init(self, thresh=0.3, box_thresh=0.5, max_candidates=1000, unclip_ratio=2.0):
self.min_size = 3
self.thresh = thresh
self.box_thresh = box_thresh
self.max_candidates = max_candidates
self.unclip_ratio = unclip_ratio
def __call__(self, pred, height, width):
"""
batch: (image, polygons, ignore_tags
batch: a dict produced by dataloaders.
image: tensor of shape (N, C, H, W).
polygons: tensor of shape (N, K, 4, 2), the polygons of objective regions.
ignore_tags: tensor of shape (N, K), indicates whether a region is ignorable or not.
shape: the original shape of images.
filename: the original filenames of images.
pred:
binary: text region segmentation map, with shape (N, H, W)
thresh: [if exists] thresh hold prediction with shape (N, H, W)
thresh_binary: [if exists] binarized with threshhold, (N, H, W)
"""
pred = pred[0, :, :]
segmentation = self.binarize(pred)
boxes, scores = self.boxes_from_bitmap(pred, segmentation, width, height)
return boxes, scores
def binarize(self, pred):
return pred > self.thresh
def boxes_from_bitmap(self, pred, bitmap, dest_width, dest_height):
"""
_bitmap: single map with shape (H, W),
whose values are binarized as {0, 1}
"""
assert len(bitmap.shape) == 2
height, width = bitmap.shape
contours, _ = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
num_contours = min(len(contours), self.max_candidates)
boxes = np.zeros((num_contours, 4, 2), dtype=np.int16)
scores = np.zeros((num_contours,), dtype=np.float32)
for index in range(num_contours):
contour = contours[index].squeeze(1)
points, sside = self.get_mini_boxes(contour)
if sside < self.min_size:
continue
points = np.array(points)
score = self.box_score_fast(pred, contour)
if self.box_thresh > score:
continue
box = self.unclip(points, unclip_ratio=self.unclip_ratio).reshape(-1, 1, 2)
box, sside = self.get_mini_boxes(box)
if sside < self.min_size + 2:
continue
box = np.array(box)
if not isinstance(dest_width, int):
dest_width = dest_width.item()
dest_height = dest_height.item()
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[index, :, :] = box.astype(np.int16)
scores[index] = score
return boxes, scores
def unclip(self, box, unclip_ratio=1.5):
poly = Polygon(box)
distance = poly.area * unclip_ratio / (poly.length if poly.length != 0 else 1) # Safely handle zero length
offset = pyclipper.PyclipperOffset()
offset.AddPath(box, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
expanded = np.array(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]) if bounding_box[1][0] > 0 and bounding_box[1][1] > 0 else 0
def box_score_fast(self, bitmap, _box):
h, w = bitmap.shape[:2]
box = _box.copy()
# 【BUG修复处】将所有的 np.int 替换为 Python 内置的 int
xmin = np.clip(np.floor(box[:, 0].min()).astype(int), 0, w - 1)
xmax = np.clip(np.ceil(box[:, 0].max()).astype(int), 0, w - 1)
ymin = np.clip(np.floor(box[:, 1].min()).astype(int), 0, h - 1)
ymax = np.clip(np.ceil(box[:, 1].max()).astype(int), 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(np.int32), 1)
return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0]
Metadata
Metadata
Assignees
Labels
No labels