forked from axinc-ai/ailia-models
-
Notifications
You must be signed in to change notification settings - Fork 0
/
hps_utils.py
86 lines (66 loc) · 2.6 KB
/
hps_utils.py
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
import numpy as np
import cv2
def xywh2cs(x, y, w, h):
center = np.zeros((2), dtype=np.float32)
center[0] = x + w * 0.5
center[1] = y + h * 0.5
aspect_ratio = 1
if w > aspect_ratio * h:
h = w * 1.0 / aspect_ratio
elif w < aspect_ratio * h:
w = h * aspect_ratio
scale = np.array([w, h], dtype=np.float32)
return center, scale
def _get_3rd_point(a, b):
direct = a - b
return b + np.array([-direct[1], direct[0]], dtype=np.float32)
def _get_dir(src_point, rot_rad):
sn, cs = np.sin(rot_rad), np.cos(rot_rad)
src_result = [0, 0]
src_result[0] = src_point[0] * cs - src_point[1] * sn
src_result[1] = src_point[0] * sn + src_point[1] * cs
return src_result
def transform_logits(logits, center, scale, width, height, input_size):
trans = get_affine_transform(center, scale, 0, input_size, inv=1)
channel = logits.shape[2]
target_logits = []
for i in range(channel):
target_logit = cv2.warpAffine(
logits[:, :, i],
trans,
(int(width), int(height)), # (int(width), int(height)),
flags=cv2.INTER_LINEAR,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(0))
target_logits.append(target_logit)
target_logits = np.stack(target_logits, axis=2)
return target_logits
def get_affine_transform(center,
scale,
rot,
output_size,
shift=np.array([0, 0], dtype=np.float32),
inv=0):
if not isinstance(scale, np.ndarray) and not isinstance(scale, list):
print(scale)
scale = np.array([scale, scale])
scale_tmp = scale
src_w = scale_tmp[0]
dst_w = output_size[1]
dst_h = output_size[0]
rot_rad = np.pi * rot / 180
src_dir = _get_dir([0, src_w * -0.5], rot_rad)
dst_dir = np.array([0, (dst_w - 1) * -0.5], np.float32)
src = np.zeros((3, 2), dtype=np.float32)
dst = np.zeros((3, 2), dtype=np.float32)
src[0, :] = center + scale_tmp * shift
src[1, :] = center + src_dir + scale_tmp * shift
dst[0, :] = [(dst_w - 1) * 0.5, (dst_h - 1) * 0.5]
dst[1, :] = np.array([(dst_w - 1) * 0.5, (dst_h - 1) * 0.5]) + dst_dir
src[2:, :] = _get_3rd_point(src[0, :], src[1, :])
dst[2:, :] = _get_3rd_point(dst[0, :], dst[1, :])
if inv:
trans = cv2.getAffineTransform(np.float32(dst), np.float32(src))
else:
trans = cv2.getAffineTransform(np.float32(src), np.float32(dst))
return trans