-
Notifications
You must be signed in to change notification settings - Fork 22
/
test.py
executable file
·208 lines (171 loc) · 7.92 KB
/
test.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
from __future__ import print_function
import os
import argparse
import torch
import torch.backends.cudnn as cudnn
import numpy as np
from data import cfg
from layers.functions.prior_box import PriorBox
from utils.nms_wrapper import nms
import cv2
from models.faceboxes import FaceBoxes
from utils.box_utils import decode
from utils.timer import Timer
parser = argparse.ArgumentParser(description='FaceBoxes')
parser.add_argument('-m', '--trained_model', default='weights/Final_HandBoxes.pth',
type=str, help='Trained state_dict file path to open')
parser.add_argument('--cpu', action="store_true", default=False, help='Use cpu inference')
parser.add_argument('--video', default='data/video/hand.avi', type=str, help='dataset')
parser.add_argument('--image', default=None, type=str, help='dataset')
parser.add_argument('--confidence_threshold', default=0.2, type=float, help='confidence_threshold')
parser.add_argument('--top_k', default=5000, type=int, help='top_k')
parser.add_argument('--nms_threshold', default=0.2, type=float, help='nms_threshold')
parser.add_argument('--keep_top_k', default=750, type=int, help='keep_top_k')
args = parser.parse_args()
def check_keys(model, pretrained_state_dict):
ckpt_keys = set(pretrained_state_dict.keys())
model_keys = set(model.state_dict().keys())
used_pretrained_keys = model_keys & ckpt_keys
unused_pretrained_keys = ckpt_keys - model_keys
missing_keys = model_keys - ckpt_keys
print('Missing keys:{}'.format(len(missing_keys)))
print('Unused checkpoint keys:{}'.format(len(unused_pretrained_keys)))
print('Used keys:{}'.format(len(used_pretrained_keys)))
assert len(used_pretrained_keys) > 0, 'load NONE from pretrained checkpoint'
return True
def remove_prefix(state_dict, prefix):
''' Old style model is stored with all names of parameters sharing common prefix 'module.' '''
print('remove prefix \'{}\''.format(prefix))
f = lambda x: x.split(prefix, 1)[-1] if x.startswith(prefix) else x
return {f(key): value for key, value in state_dict.items()}
def load_model(model, pretrained_path, load_to_cpu):
print('Loading pretrained model from {}'.format(pretrained_path))
if load_to_cpu:
pretrained_dict = torch.load(pretrained_path, map_location=lambda storage, loc: storage)
else:
device = torch.cuda.current_device()
pretrained_dict = torch.load(pretrained_path, map_location=lambda storage, loc: storage.cuda(device))
if "state_dict" in pretrained_dict.keys():
pretrained_dict = remove_prefix(pretrained_dict['state_dict'], 'module.')
else:
pretrained_dict = remove_prefix(pretrained_dict, 'module.')
check_keys(model, pretrained_dict)
model.load_state_dict(pretrained_dict, strict=False)
return model
if __name__ == '__main__':
torch.set_grad_enabled(False)
# net and model
net = FaceBoxes(phase='test', size=None, num_classes=2) # initialize detector
net = load_model(net, args.trained_model, args.cpu)
net.eval()
print('Finished loading model!')
print(net)
cudnn.benchmark = True
device = torch.device("cpu" if args.cpu else "cuda")
net = net.to(device)
# testing scale
resize = 2
_t = {'forward_pass': Timer(), 'misc': Timer()}
if args.image:
to_show = cv2.imread(args.image, cv2.IMREAD_COLOR)
img = np.float32(to_show)
if resize != 1:
img = cv2.resize(img, None, None, fx=resize, fy=resize, interpolation=cv2.INTER_LINEAR)
im_height, im_width, _ = img.shape
scale = torch.Tensor([img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
img -= (104, 117, 123)
img = img.transpose(2, 0, 1)
img = torch.from_numpy(img).unsqueeze(0)
img = img.to(device)
scale = scale.to(device)
_t['forward_pass'].tic()
out = net(img) # forward pass
_t['forward_pass'].toc()
_t['misc'].tic()
priorbox = PriorBox(cfg, out[2], (im_height, im_width), phase='test')
priors = priorbox.forward()
priors = priors.to(device)
loc, conf, _ = out
prior_data = priors.data
boxes = decode(loc.data.squeeze(0), prior_data, cfg['variance'])
boxes = boxes * scale / resize
boxes = boxes.cpu().numpy()
scores = conf.data.cpu().numpy()[:, 1]
# ignore low scores
inds = np.where(scores > args.confidence_threshold)[0]
boxes = boxes[inds]
scores = scores[inds]
# keep top-K before NMS
order = scores.argsort()[::-1][:args.top_k]
boxes = boxes[order]
scores = scores[order]
# do NMS
dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
#keep = py_cpu_nms(dets, args.nms_threshold)
keep = nms(dets, args.nms_threshold, force_cpu=args.cpu)
dets = dets[keep, :]
# keep top-K faster NMS
dets = dets[:args.keep_top_k, :]
_t['misc'].toc()
for i in range(dets.shape[0]):
cv2.rectangle(to_show, (dets[i][0], dets[i][1]), (dets[i][2], dets[i][3]), [0, 0, 255], 3)
cv2.imshow('image', to_show)
cv2.waitKey(0)
cv2.destroyAllWindows()
else:
videofile = args.video
cap = cv2.VideoCapture(videofile)
assert cap.isOpened(), 'Cannot capture source'
while cap.isOpened():
ret, frame = cap.read()
if ret:
to_show = frame
img = np.float32(to_show)
if resize != 1:
img = cv2.resize(img, None, None, fx=resize, fy=resize, interpolation=cv2.INTER_LINEAR)
im_height, im_width, _ = img.shape
scale = torch.Tensor([img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
img -= (104, 117, 123)
img = img.transpose(2, 0, 1)
img = torch.from_numpy(img).unsqueeze(0)
img = img.to(device)
scale = scale.to(device)
_t['forward_pass'].tic()
out = net(img) # forward pass
_t['forward_pass'].toc()
_t['misc'].tic()
priorbox = PriorBox(cfg, out[2], (im_height, im_width), phase='test')
priors = priorbox.forward()
priors = priors.to(device)
loc, conf, _ = out
prior_data = priors.data
boxes = decode(loc.data.squeeze(0), prior_data, cfg['variance'])
boxes = boxes * scale / resize
boxes = boxes.cpu().numpy()
scores = conf.data.cpu().numpy()[:, 1]
# ignore low scores
inds = np.where(scores > args.confidence_threshold)[0]
boxes = boxes[inds]
scores = scores[inds]
# keep top-K before NMS
order = scores.argsort()[::-1][:args.top_k]
boxes = boxes[order]
scores = scores[order]
# do NMS
dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
# keep = py_cpu_nms(dets, args.nms_threshold)
keep = nms(dets, args.nms_threshold, force_cpu=args.cpu)
dets = dets[keep, :]
# keep top-K faster NMS
dets = dets[:args.keep_top_k, :]
_t['misc'].toc()
for i in range(dets.shape[0]):
cv2.rectangle(to_show, (dets[i][0], dets[i][1]), (dets[i][2], dets[i][3]), [0, 0, 255], 3)
cv2.imshow('image', to_show)
# cv2.waitKey(0)
# cv2.destroyAllWindows()
key = cv2.waitKey(1)
if key & 0xFF == ord('q'):
break
else:
break