Newer
Older
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
from __future__ import division
import time
import torch
import torch.nn as nn
from torch.autograd import Variable
import numpy as np
import cv2
from util import *
from darknet import Darknet
from preprocess import prep_image, inp_to_image, letterbox_image
import pandas as pd
import random
import pickle as pkl
import argparse
def get_test_input(input_dim, CUDA):
img = cv2.imread("dog-cycle-car.png")
img = cv2.resize(img, (input_dim, input_dim))
img_ = img[:,:,::-1].transpose((2,0,1))
img_ = img_[np.newaxis,:,:,:]/255.0
img_ = torch.from_numpy(img_).float()
img_ = Variable(img_)
if CUDA:
img_ = img_.cuda()
return img_
def prep_image(img, inp_dim):
"""
Prepare image for inputting to the neural network.
Returns a Variable
"""
orig_im = img
dim = orig_im.shape[1], orig_im.shape[0]
img = (letterbox_image(orig_im, (inp_dim, inp_dim)))
img_ = img[:,:,::-1].transpose((2,0,1)).copy()
img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
return img_, orig_im, dim
def write(x, img):
c1 = tuple(x[1:3].int())
c2 = tuple(x[3:5].int())
cls = int(x[-1])
label = "{0}".format(classes[cls])
color = random.choice(colors)
cv2.rectangle(img, c1, c2,color, 1)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 1 , 1)[0]
c2 = c1[0] + t_size[0] + 3, c1[1] + t_size[1] + 4
cv2.rectangle(img, c1, c2,color, -1)
cv2.putText(img, label, (c1[0], c1[1] + t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 1, [225,255,255], 1);
return img
def arg_parse():
"""
Parse arguements to the detect module
"""
parser = argparse.ArgumentParser(description='YOLO v2 Video Detection Module')
parser.add_argument("--video", dest = 'video', help =
"Video to run detection upon",
default = "video.avi", type = str)
parser.add_argument("--dataset", dest = "dataset", help = "Dataset on which the network has been trained", default = "pascal")
parser.add_argument("--confidence", dest = "confidence", help = "Object Confidence to filter predictions", default = 0.5)
parser.add_argument("--nms_thresh", dest = "nms_thresh", help = "NMS Threshhold", default = 0.4)
parser.add_argument("--cfg", dest = 'cfgfile', help =
"Config file",
default = "cfg/yolov3.cfg", type = str)
parser.add_argument("--weights", dest = 'weightsfile', help =
"weightsfile",
default = "yolov3.weights", type = str)
parser.add_argument("--reso", dest = 'reso', help =
"Input resolution of the network. Increase to increase accuracy. Decrease to increase speed",
default = "416", type = str)
return parser.parse_args()
if __name__ == '__main__':
args = arg_parse()
confidence = float(args.confidence)
nms_thesh = float(args.nms_thresh)
start = 0
CUDA = torch.cuda.is_available()
CUDA = torch.cuda.is_available()
num_classes = 80
bbox_attrs = 5 + num_classes
print("Loading network.....")
model = Darknet(args.cfgfile)
model.load_weights(args.weightsfile)
print("Network successfully loaded")
model.net_info["height"] = args.reso
inp_dim = int(model.net_info["height"])
assert inp_dim % 32 == 0
assert inp_dim > 32
if CUDA:
model.cuda().half()
model(get_test_input(inp_dim, CUDA), CUDA)
model.eval()
videofile = 'video.avi'
cap = cv2.VideoCapture(videofile)
assert cap.isOpened(), 'Cannot capture source'
frames = 0
start = time.time()
while cap.isOpened():
ret, frame = cap.read()
if ret:
img, orig_im, dim = prep_image(frame, inp_dim)
im_dim = torch.FloatTensor(dim).repeat(1,2)
if CUDA:
img = img.cuda().half()
im_dim = im_dim.half().cuda()
write_results = write_results_half
predict_transform = predict_transform_half
output = model(Variable(img, volatile = True), CUDA)
output = write_results(output, confidence, num_classes, nms = True, nms_conf = nms_thesh)
if type(output) == int:
frames += 1
print("FPS of the video is {:5.2f}".format( frames / (time.time() - start)))
cv2.imshow("frame", orig_im)
key = cv2.waitKey(1)
if key & 0xFF == ord('q'):
break
continue
im_dim = im_dim.repeat(output.size(0), 1)
scaling_factor = torch.min(inp_dim/im_dim,1)[0].view(-1,1)
output[:,[1,3]] -= (inp_dim - scaling_factor*im_dim[:,0].view(-1,1))/2
output[:,[2,4]] -= (inp_dim - scaling_factor*im_dim[:,1].view(-1,1))/2
output[:,1:5] /= scaling_factor
for i in range(output.shape[0]):
output[i, [1,3]] = torch.clamp(output[i, [1,3]], 0.0, im_dim[i,0])
output[i, [2,4]] = torch.clamp(output[i, [2,4]], 0.0, im_dim[i,1])
classes = load_classes('data/coco.names')
colors = pkl.load(open("pallete", "rb"))
list(map(lambda x: write(x, orig_im), output))
cv2.imshow("frame", orig_im)
key = cv2.waitKey(1)
if key & 0xFF == ord('q'):
break
frames += 1
print("FPS of the video is {:5.2f}".format( frames / (time.time() - start)))
else:
break