-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathanchors.py
149 lines (114 loc) · 5.25 KB
/
anchors.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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
import numpy as np
import torch
import torch.nn as nn
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
def generate_anchors(base_size=16, ratios=None, scales=None):
if ratios is None:
ratios = np.array([0.5, 1, 2])
if scales is None:
scales = np.array([2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)])
num_anchors = len(ratios) * len(scales)
anchors = np.zeros((num_anchors, 4))
anchors[:, 2:] = base_size * np.tile(scales, (2, len(ratios))).T
areas = anchors[:, 2] * anchors[:, 3]
anchors[:, 2] = np.sqrt(areas / np.repeat(ratios, len(scales)))
anchors[:, 3] = anchors[:, 2] * np.repeat(ratios, len(scales))
anchors[:, 0::2] -= np.tile(anchors[:, 2] * 0.5, (2, 1)).T
anchors[:, 1::2] -= np.tile(anchors[:, 3] * 0.5, (2, 1)).T
return anchors
def compute_shape(image_shape, pyramid_levels):
image_shape = np.array(image_shape[:2])
image_shapes = [(image_shape + 2 ** x - 1) // (2 ** x) for x in pyramid_levels]
return image_shapes
def anchors_for_shape(
image_shape,
pyramid_levels=None,
ratios=None,
scales=None,
strides=None,
sizes=None,
):
image_shapes = compute_shape(image_shape, pyramid_levels)
all_anchors = np.zeros((0, 4))
for idx, p in enumerate(pyramid_levels):
anchors = generate_anchors(base_size=sizes[idx], ratios=ratios, scales=scales)
shifted_anchors = shift(image_shapes[idx], strides[idx], anchors)
all_anchors = np.append(all_anchors, shifted_anchors, axis=0)
return all_anchors
def shift(shape, stride, anchors):
shift_x = (np.arange(0, shape[1]) + 0.5) * stride
shift_y = (np.arange(0, shape[0]) + 0.5) * stride
shift_x, shift_y = np.meshgrid(shift_x, shift_y)
shifts = np.vstack((
shift_x.ravel(), shift_y.ravel(),
shift_x.ravel(), shift_y.ravel()
)).transpose()
A = anchors.shape[0]
K = shifts.shape[0]
all_anchors = (anchors.reshape((1, A, 4)) + shifts.reshape((1, K, 4)).transpose((1, 0, 2)))
all_anchors = all_anchors.reshape((K * A, 4))
return all_anchors
class Anchors(nn.Module):
def __init__(self, pyramid_level=None, strides=None, sizes=None, ratios=None, scales=None):
super(Anchors, self).__init__()
if pyramid_level is None:
self.pyramid_levels = [3,4,5,6,7]
if strides is None:
self.strides = [2 ** x for x in self.pyramid_levels]
if sizes is None:
self.sizes = [2 ** (x+2) for x in self.pyramid_levels]
if ratios is None:
self.ratios = np.array([0.5, 1, 2])
if scales is None:
self.scales = np.array([2**0, 2**(1.0/3.0), 2**(2.0/3.0)])
def forward(self, image):
image_shape = image.shape[2:]
image_shape = np.array(image_shape)
image_shapes = [(image_shape + 2 ** x - 1) // (2 ** x) for x in self.pyramid_levels]
anchors_all = np.zeros((0, 4)).astype(np.float32)
for idx, p in enumerate(self.pyramid_levels):
anchors = generate_anchors(base_size=self.sizes[idx], ratios=self.ratios, scales=self.scales)
shifted_anchors = shift(image_shapes[idx], self.strides[idx], anchors)
anchors_all = np.append(anchors_all, shifted_anchors, axis=0)
anchors_all = np.expand_dims(anchors_all, axis=0)
return torch.from_numpy(anchors_all.astype(np.float32)).to(device)
class BoundingBoxTransform(nn.Module):
def __init__(self, mean=None, std=None):
super(BoundingBoxTransform, self).__init__()
if mean is None:
self.mean = torch.from_numpy(np.array([0, 0, 0, 0]).astype(np.float32)).to(device)
else:
self.mean = mean
if std is None:
self.std = torch.from_numpy(np.array([0.1, 0.1, 0.2, 0.2]).astype(np.float32)).to(device)
else:
self.std = std
def forward(self, boxes, deltas):
widths = boxes[:, :, 2] - boxes[:, :, 0]
heights = boxes[:, :, 3] - boxes[:, :, 1]
ctr_x = boxes[:, :, 0] + 0.5 * widths
ctr_y = boxes[:, :, 1] + 0.5 * heights
dx = deltas[:, :, 0] * self.std[0] + self.mean[0]
dy = deltas[:, :, 1] * self.std[1] + self.mean[1]
dw = deltas[:, :, 2] * self.std[2] + self.mean[2]
dh = deltas[:, :, 3] * self.std[3] + self.mean[3]
pred_ctr_x = ctr_x + dx * widths
pred_ctr_y = ctr_y + dy * heights
pred_w = torch.exp(dw) * widths
pred_h = torch.exp(dh) * heights
pred_boxes_x1 = pred_ctr_x - 0.5 * pred_w
pred_boxes_y1 = pred_ctr_y - 0.5 * pred_h
pred_boxes_x2 = pred_ctr_x + 0.5 * pred_w
pred_boxes_y2 = pred_ctr_y + 0.5 * pred_h
pred_boxes = torch.stack([pred_boxes_x1, pred_boxes_y1, pred_boxes_x2, pred_boxes_y2], dim=2)
return pred_boxes
class ClipBoxes(nn.Module):
def __init__(self, width=None, height=None):
super(ClipBoxes, self).__init__()
def forward(self, boxes, img):
batch_size, num_channels, height, width = img.shape
boxes[:, :, 0] = torch.clamp(boxes[:, :, 0], min=0)
boxes[:, :, 1] = torch.clamp(boxes[:, :, 1], min=0)
boxes[:, :, 2] = torch.clamp(boxes[:, :, 2], max=width)
boxes[:, :, 3] = torch.clamp(boxes[:, :, 3], max=height)
return boxes