-
Notifications
You must be signed in to change notification settings - Fork 34
/
Copy pathssha_detector.py
216 lines (181 loc) · 8.87 KB
/
ssha_detector.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
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
from __future__ import print_function
import sys
import cv2
import mxnet as mx
from mxnet import ndarray as nd
import numpy as np
import numpy.random as npr
from distutils.util import strtobool
from rcnn.processing.bbox_transform import nonlinear_pred, clip_boxes, kpoint_pred, clip_points
from rcnn.processing.generate_anchor import generate_anchors_fpn, anchors_plane
from rcnn.processing.nms import gpu_nms_wrapper
class SSHDetector:
def __init__(self, prefix, epoch, ctx_id=0, test_mode=False):
self.ctx_id = ctx_id
self.ctx = mx.gpu(self.ctx_id)
self.fpn_keys = []
fpn_stride = []
fpn_base_size = []
self._feat_stride_fpn = [32, 16, 8]
for s in self._feat_stride_fpn:
self.fpn_keys.append('stride%s' % s)
fpn_stride.append(int(s))
fpn_base_size.append(16)
self._scales = np.array([32, 16, 8, 4, 2, 1])
self._ratios = np.array([1.0] * len(self._feat_stride_fpn))
self._anchors_fpn = dict(
zip(self.fpn_keys, generate_anchors_fpn(base_size=fpn_base_size, scales=self._scales, ratios=self._ratios)))
self._num_anchors = dict(zip(self.fpn_keys, [anchors.shape[0] for anchors in self._anchors_fpn.values()]))
self._rpn_pre_nms_top_n = 1000
# self._rpn_post_nms_top_n = rpn_post_nms_top_n
# self.score_threshold = 0.05
self.nms_threshold = 0.3
self._bbox_pred = nonlinear_pred
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix, epoch)
# mx.viz.plot_network(sym).view()
self.nms = gpu_nms_wrapper(self.nms_threshold, self.ctx_id)
self.pixel_means = np.array([103.939, 116.779, 123.68]) # BGR
if not test_mode:
image_size = (640, 640)
self.model = mx.mod.Module(symbol=sym, context=self.ctx, label_names=None)
self.model.bind(data_shapes=[('data', (1, 3, image_size[0], image_size[1]))], for_training=False)
self.model.set_params(arg_params, aux_params)
else:
from rcnn.core.module import MutableModule
image_size = (2400, 2400)
data_shape = [('data', (1, 3, image_size[0], image_size[1]))]
self.model = MutableModule(symbol=sym, data_names=['data'], label_names=None,
context=self.ctx, max_data_shapes=data_shape)
self.model.bind(data_shape, None, for_training=False)
self.model.set_params(arg_params, aux_params)
def detect(self, img, threshold=0.5, scales=[1.0]):
proposals_list = []
proposals_kp_list = []
scores_list = []
for im_scale in scales:
if im_scale != 1.0:
im = cv2.resize(img, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
else:
im = img
im = im.astype(np.float32)
# self.model.bind(data_shapes=[('data', (1, 3, image_size[0], image_size[1]))], for_training=False)
im_info = [im.shape[0], im.shape[1], im_scale]
im_tensor = np.zeros((1, 3, im.shape[0], im.shape[1]))
for i in range(3):
im_tensor[0, i, :, :] = im[:, :, 2 - i] - self.pixel_means[2 - i]
data = nd.array(im_tensor)
print("data.shape: ", data.shape)
db = mx.io.DataBatch(data=(data,), provide_data=[('data', data.shape)])
self.model.forward(db, is_train=False)
net_out = self.model.get_outputs()
# print("net_out: ", net_out)
pre_nms_topN = self._rpn_pre_nms_top_n
# post_nms_topN = self._rpn_post_nms_top_n
# min_size_dict = self._rpn_min_size_fpn
for s in self._feat_stride_fpn:
if len(scales) > 1 and s == 32 and im_scale == scales[-1]:
continue
_key = 'stride%s' % s
stride = int(s)
idx = 0
if s == 16:
idx = 3
elif s == 8:
idx = 6
print('getting', im_scale, stride, idx, len(net_out), data.shape, file=sys.stderr)
# print("net_out", net_out)
scores = net_out[idx].asnumpy()
# print(scores.shape)
idx += 1
# print('scores',stride, scores.shape, file=sys.stderr)
scores = scores[:, self._num_anchors['stride%s' % s]:, :, :]
bbox_deltas = net_out[idx].asnumpy()
idx += 1
# if DEBUG:
# print 'im_size: ({}, {})'.format(im_info[0], im_info[1])
# print 'scale: {}'.format(im_info[2])
_height, _width = int(im_info[0] / stride), int(im_info[1] / stride)
height, width = bbox_deltas.shape[2], bbox_deltas.shape[3]
# kpoint
kpoint_deltas = net_out[idx].asnumpy()
A = self._num_anchors['stride%s' % s]
K = height * width
anchors = anchors_plane(height, width, stride, self._anchors_fpn['stride%s' % s].astype(np.float32))
# print((height, width), (_height, _width), anchors.shape, bbox_deltas.shape, scores.shape, file=sys.stderr)
anchors = anchors.reshape((K * A, 4))
# print('pre', bbox_deltas.shape, height, width)
bbox_deltas = self._clip_pad(bbox_deltas, (height, width))
# print('after', bbox_deltas.shape, height, width)
bbox_deltas = bbox_deltas.transpose((0, 2, 3, 1)).reshape((-1, 4))
kpoint_deltas = self._clip_pad(kpoint_deltas, (height, width))
kpoint_deltas = kpoint_deltas.transpose((0, 2, 3, 1)).reshape((-1, 10))
scores = self._clip_pad(scores, (height, width))
scores = scores.transpose((0, 2, 3, 1)).reshape((-1, 1))
# print(anchors.shape, bbox_deltas.shape, A, K, file=sys.stderr)
proposals = self._bbox_pred(anchors, bbox_deltas)
# proposals = anchors
proposals = clip_boxes(proposals, im_info[:2])
proposals_kp = kpoint_pred(anchors, kpoint_deltas)
proposals_kp = clip_points(proposals_kp, im_info[:2])
# keep = self._filter_boxes(proposals, min_size_dict['stride%s'%s] * im_info[2])
# proposals = proposals[keep, :]
# scores = scores[keep]
# print('333', proposals.shape)
scores_ravel = scores.ravel()
order = scores_ravel.argsort()[::-1]
if pre_nms_topN > 0:
order = order[:pre_nms_topN]
proposals = proposals[order, :]
proposals_kp = proposals_kp[order, :]
scores = scores[order]
proposals /= im_scale
proposals_kp /= im_scale
proposals_list.append(proposals)
proposals_kp_list.append(proposals_kp)
scores_list.append(scores)
proposals = np.vstack(proposals_list)
proposals_kp = np.vstack(proposals_kp_list)
scores = np.vstack(scores_list)
scores_ravel = scores.ravel()
order = scores_ravel.argsort()[::-1]
# if config.TEST.SCORE_THRESH>0.0:
# _count = np.sum(scores_ravel>config.TEST.SCORE_THRESH)
# order = order[:_count]
# if pre_nms_topN > 0:
# order = order[:pre_nms_topN]
proposals = proposals[order, :]
proposals_kp = proposals_kp[order, :]
scores = scores[order]
det = np.hstack((proposals, scores, proposals_kp)).astype(np.float32)
# if np.shape(det)[0] == 0:
# print("Something wrong with the input image(resolution is too low?), generate fake proposals for it.")
# proposals = np.array([[1.0, 1.0, 2.0, 2.0]]*post_nms_topN, dtype=np.float32)
# scores = np.array([[0.9]]*post_nms_topN, dtype=np.float32)
# det = np.array([[1.0, 1.0, 2.0, 2.0, 0.9]]*post_nms_topN, dtype=np.float32)
if self.nms_threshold < 1.0:
keep = self.nms(det)
det = det[keep, :]
if threshold > 0.0:
keep = np.where(det[:, 4] >= threshold)[0]
det = det[keep, :]
return det
@staticmethod
def _filter_boxes(boxes, min_size):
""" Remove all boxes with any side smaller than min_size """
ws = boxes[:, 2] - boxes[:, 0] + 1
hs = boxes[:, 3] - boxes[:, 1] + 1
keep = np.where((ws >= min_size) & (hs >= min_size))[0]
return keep
@staticmethod
def _clip_pad(tensor, pad_shape):
"""
Clip boxes of the pad area.
:param tensor: [n, c, H, W]
:param pad_shape: [h, w]
:return: [n, c, h, w]
"""
H, W = tensor.shape[2:]
h, w = pad_shape
if h < H or w < W:
tensor = tensor[:, :, :h, :w].copy()
return tensor