-
Notifications
You must be signed in to change notification settings - Fork 1
/
demo.py
208 lines (178 loc) · 7.15 KB
/
demo.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
import argparse
import cv2
import numpy as np
import os
import torch
import torch.backends.cudnn as cudnn
from torch.autograd import Variable
from data import BaseTransform, VOC_300
from data import VOC_CLASSES as labelmap
from layers.functions import Detect, PriorBox
from utils.timer import Timer
parser = argparse.ArgumentParser(description='Receptive Field Block Net')
parser.add_argument('-v', '--version', default='RFB_vgg',
help='RFB_vgg ,RFB_E_vgg or RFB_mobile version.')
parser.add_argument('-s', '--size', default='300',
help='300 or 512 input size.')
parser.add_argument('-d', '--dataset', default='VOC',
help='VOC or COCO version')
parser.add_argument('-m', '--trained_model', default=r'weights/7690.pth',
type=str, help='Trained state_dict file path to open')
parser.add_argument('--save_folder', default='eval/', type=str,
help='Dir to save results')
parser.add_argument('--video', default=True, type=bool,
help='test cache results')
args = parser.parse_args()
if not os.path.exists(args.save_folder):
os.mkdir(args.save_folder)
cfg = VOC_300,
if args.version == 'RFB_vgg':
from models.RFB_Net_vgg import build_net
elif args.version == 'RFB_E_vgg':
from models.RFB_Net_E_vgg import build_net
priorbox = PriorBox(cfg)
with torch.no_grad():
priors = priorbox.forward()
def py_cpu_nms(dets, thresh):
"""Pure Python NMS baseline."""
x1 = dets[:, 0]
y1 = dets[:, 1]
x2 = dets[:, 2]
y2 = dets[:, 3]
scores = dets[:, 4]
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
order = scores.argsort()[::-1]
keep = []
while order.size > 0:
i = order[0]
keep.append(i)
xx1 = np.maximum(x1[i], x1[order[1:]])
yy1 = np.maximum(y1[i], y1[order[1:]])
xx2 = np.minimum(x2[i], x2[order[1:]])
yy2 = np.minimum(y2[i], y2[order[1:]])
w = np.maximum(0.0, xx2 - xx1 + 1)
h = np.maximum(0.0, yy2 - yy1 + 1)
inter = w * h
ovr = inter / (areas[i] + areas[order[1:]] - inter)
inds = np.where(ovr <= thresh)[0]
order = order[inds + 1]
return keep
class ObjectDetector:
def __init__(self, net, detection, transform, num_classes=21, max_per_image=300, thresh=0.5):
self.net = net
self.detection = detection
self.transform = transform
self.max_per_image = 300
self.num_classes = num_classes
self.max_per_image = max_per_image
self.thresh = thresh
def predict(self, img):
scale = torch.Tensor([img.shape[1], img.shape[0],
img.shape[1], img.shape[0]]).cpu().numpy()
assert img.shape[2] == 3
with torch.no_grad():
x = transform(img).unsqueeze(0)
_t['im_detect'].tic()
out = net(x) # forward pass
boxes, scores = self.detection.forward(out, priors)
detect_time = _t['im_detect'].toc()
boxes = boxes[0]
scores = scores[0]
boxes = boxes.cpu().numpy()
scores = scores.cpu().numpy()
# scale each detection back up to the image
boxes *= scale
_t['misc'].tic()
all_boxes = [[] for _ in range(num_classes)]
for j in range(1, num_classes):
inds = np.where(scores[:, j] > self.thresh)[0]
if len(inds) == 0:
all_boxes[j] = np.zeros([0, 5], dtype=np.float32)
continue
c_bboxes = boxes[inds]
c_scores = scores[inds, j]
#print(scores[:, j])
c_dets = np.hstack((c_bboxes, c_scores[:, np.newaxis])).astype(
np.float32, copy=False)
# keep = nms(c_bboxes,c_scores)
keep = py_cpu_nms(c_dets, 0.45)
keep = keep[:30]
c_dets = c_dets[keep, :]
all_boxes[j] = c_dets
if self.max_per_image > 0:
image_scores = np.hstack([all_boxes[j][:, -1] for j in range(1, num_classes)])
if len(image_scores) > self.max_per_image:
image_thresh = np.sort(image_scores)[-self.max_per_image]
for j in range(1, num_classes):
keep = np.where(all_boxes[j][:, -1] >= image_thresh)[0]
all_boxes[j] = all_boxes[j][keep, :]
nms_time = _t['misc'].toc()
total_time = detect_time+nms_time
#print('total time: ', total_time)
return all_boxes, total_time
COLORS = [(255, 0, 0), (0, 255, 0), (0, 0, 255)]
FONT = cv2.FONT_HERSHEY_SIMPLEX
if __name__ == '__main__':
# load net
img_dim = 300
num_classes = 2
_t = {'im_detect': Timer(), 'misc': Timer()}
net = build_net('test', num_classes) # initialize detector
state_dict = torch.load(args.trained_model, map_location='cpu')
# create new OrderedDict that does not contain `module.`
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in state_dict.items():
head = k[:7]
if head == 'module.':
name = k[7:] # remove `module.`
else:
name = k
new_state_dict[name] = v
net.load_state_dict(new_state_dict)
net.eval()
print('Finished loading model!')
print(net)
# evaluation
top_k = 30
detector = Detect(num_classes, 0, cfg)
rgb_means = (104, 117, 123)
rgb_std = (1, 1, 1)
transform = BaseTransform(img_dim, rgb_means, (2, 0, 1))
object_detector = ObjectDetector(net, detector, transform)
cap = cv2.VideoCapture('eval/1.mp4')
ti = 0
totalTime = 0
while True:
ti += 1
ret, image = cap.read()
detect_bboxes, time = object_detector.predict(image)
totalTime += time
if ti % 20 == 0:
print('im_detect: {:.3f}s'.format(totalTime/ti))
totalTime = 0
ti = 0
for class_id, class_collection in enumerate(detect_bboxes):
if len(class_collection) > 0:
for i in range(class_collection.shape[0]):
if class_collection[i, -1] > 0.6:
pt = class_collection[i]
cv2.rectangle(image, (int(pt[0]), int(pt[1])), (int(pt[2]),
int(pt[3])), COLORS[i % 3], 2)
cv2.putText(image, labelmap[class_id], (int(pt[0]), int(pt[1])), FONT,
1, (255, 255, 255), 3)
cv2.imshow('result', image)
cv2.waitKey(10)
# image = cv2.imread('eval/2.jpg')
# detect_bboxes = object_detector.predict(image)
# for class_id,class_collection in enumerate(detect_bboxes):
# if len(class_collection)>0:
# for i in range(class_collection.shape[0]):
# if class_collection[i,-1]>0.6:
# pt = class_collection[i]
# cv2.rectangle(image, (int(pt[0]), int(pt[1])), (int(pt[2]),
# int(pt[3])), COLORS[i % 3], 2)
# cv2.putText(image, labelmap[class_id], (int(pt[0]), int(pt[1])), FONT,
# 0.5, (255, 255, 255), 2)
# cv2.imshow('result',image)
# cv2.waitKey()