-
Notifications
You must be signed in to change notification settings - Fork 878
/
boxes.py
133 lines (108 loc) · 4.36 KB
/
boxes.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
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
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
# Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
import numpy as np
import torch
import torchvision
import torch.nn.functional as F
__all__ = [
"filter_box",
"postprocess",
"bboxes_iou",
"matrix_iou",
"adjust_box_anns",
"xyxy2xywh",
"xyxy2cxcywh",
]
def filter_box(output, scale_range):
"""
output: (N, 5+class) shape
"""
min_scale, max_scale = scale_range
w = output[:, 2] - output[:, 0]
h = output[:, 3] - output[:, 1]
keep = (w * h > min_scale * min_scale) & (w * h < max_scale * max_scale)
return output[keep]
def postprocess(prediction, num_classes, conf_thre=0.7, nms_thre=0.45):
box_corner = prediction.new(prediction.shape)
box_corner[:, :, 0] = prediction[:, :, 0] - prediction[:, :, 2] / 2
box_corner[:, :, 1] = prediction[:, :, 1] - prediction[:, :, 3] / 2
box_corner[:, :, 2] = prediction[:, :, 0] + prediction[:, :, 2] / 2
box_corner[:, :, 3] = prediction[:, :, 1] + prediction[:, :, 3] / 2
prediction[:, :, :4] = box_corner[:, :, :4]
output = [None for _ in range(len(prediction))]
for i, image_pred in enumerate(prediction):
# If none are remaining => process next image
if not image_pred.size(0):
continue
# Get score and class with highest confidence
class_conf, class_pred = torch.max(
image_pred[:, 5 : 5 + num_classes], 1, keepdim=True
)
conf_mask = (image_pred[:, 4] * class_conf.squeeze() >= conf_thre).squeeze()
# _, conf_mask = torch.topk((image_pred[:, 4] * class_conf.squeeze()), 1000)
# Detections ordered as (x1, y1, x2, y2, obj_conf, class_conf, class_pred)
detections = torch.cat((image_pred[:, :5], class_conf, class_pred.float()), 1)
detections = detections[conf_mask]
if not detections.size(0):
continue
nms_out_index = torchvision.ops.batched_nms(
detections[:, :4],
detections[:, 4] * detections[:, 5],
detections[:, 6],
nms_thre,
)
detections = detections[nms_out_index]
if output[i] is None:
output[i] = detections
else:
output[i] = torch.cat((output[i], detections))
return output
def bboxes_iou(bboxes_a, bboxes_b, xyxy=True):
if bboxes_a.shape[1] != 4 or bboxes_b.shape[1] != 4:
raise IndexError
if xyxy:
tl = torch.max(bboxes_a[:, None, :2], bboxes_b[:, :2])
br = torch.min(bboxes_a[:, None, 2:], bboxes_b[:, 2:])
area_a = torch.prod(bboxes_a[:, 2:] - bboxes_a[:, :2], 1)
area_b = torch.prod(bboxes_b[:, 2:] - bboxes_b[:, :2], 1)
else:
tl = torch.max(
(bboxes_a[:, None, :2] - bboxes_a[:, None, 2:] / 2),
(bboxes_b[:, :2] - bboxes_b[:, 2:] / 2),
)
br = torch.min(
(bboxes_a[:, None, :2] + bboxes_a[:, None, 2:] / 2),
(bboxes_b[:, :2] + bboxes_b[:, 2:] / 2),
)
area_a = torch.prod(bboxes_a[:, 2:], 1)
area_b = torch.prod(bboxes_b[:, 2:], 1)
en = (tl < br).type(tl.type()).prod(dim=2)
area_i = torch.prod(br - tl, 2) * en # * ((tl < br).all())
return area_i / (area_a[:, None] + area_b - area_i)
def matrix_iou(a, b):
"""
return iou of a and b, numpy version for data augenmentation
"""
lt = np.maximum(a[:, np.newaxis, :2], b[:, :2])
rb = np.minimum(a[:, np.newaxis, 2:], b[:, 2:])
area_i = np.prod(rb - lt, axis=2) * (lt < rb).all(axis=2)
area_a = np.prod(a[:, 2:] - a[:, :2], axis=1)
area_b = np.prod(b[:, 2:] - b[:, :2], axis=1)
return area_i / (area_a[:, np.newaxis] + area_b - area_i + 1e-12)
def adjust_box_anns(bbox, scale_ratio, padw, padh, w_max, h_max):
#bbox[:, 0::2] = np.clip(bbox[:, 0::2] * scale_ratio + padw, 0, w_max)
#bbox[:, 1::2] = np.clip(bbox[:, 1::2] * scale_ratio + padh, 0, h_max)
bbox[:, 0::2] = bbox[:, 0::2] * scale_ratio + padw
bbox[:, 1::2] = bbox[:, 1::2] * scale_ratio + padh
return bbox
def xyxy2xywh(bboxes):
bboxes[:, 2] = bboxes[:, 2] - bboxes[:, 0]
bboxes[:, 3] = bboxes[:, 3] - bboxes[:, 1]
return bboxes
def xyxy2cxcywh(bboxes):
bboxes[:, 2] = bboxes[:, 2] - bboxes[:, 0]
bboxes[:, 3] = bboxes[:, 3] - bboxes[:, 1]
bboxes[:, 0] = bboxes[:, 0] + bboxes[:, 2] * 0.5
bboxes[:, 1] = bboxes[:, 1] + bboxes[:, 3] * 0.5
return bboxes