-
Notifications
You must be signed in to change notification settings - Fork 0
/
detector.py
215 lines (161 loc) · 6.83 KB
/
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
import time
import torch
import torch.nn as nn
from torch.autograd import Variable
import numpy as np
import cv2
from utils import *
import argparse
import os
import os.path as osp
from darknet import Darknet
import pickle as pkl
import pandas as pd
import random
def arg_parse():
"""
Parse arguements to the detect module
"""
parser = argparse.ArgumentParser(description='YOLO v3 Detection Module')
parser.add_argument("--images", dest = 'images', help =
"Image / Directory containing images to perform detection upon",
default = "imgs", type = str)
parser.add_argument("--det", dest = 'det', help =
"Image / Directory to store detections to",
default = "det", type = str)
parser.add_argument("--bs", dest = "bs", help = "Batch size", default = 1)
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()
args = arg_parse()
images = args.images
batch_size = int(args.bs)
confidence = float(args.confidence)
nms_thesh = float(args.nms_thresh)
start = 0
CUDA = torch.cuda.is_available()
num_classes = 80
classes = load_classes("data/coco.names")
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()
model.eval()
read_dir = time.time()
try:
imlist = [osp.join(osp.realpath('.'), images, img) for img in os.listdir(images)]
except NotADirectoryError:
imlist = []
imlist.append(osp.join(osp.realpath('.'), images))
except FileNotFoundError:
print ("No file or directory with the name {}".format(images))
exit()
if not os.path.exists(args.det):
os.makedirs(args.det)
load_batch = time.time()
loaded_ims = [cv2.imread(x) for x in imlist]
im_batches = list(map(prep_image, loaded_ims, [inp_dim for x in range(len(imlist))]))
im_dim_list = [(x.shape[1], x.shape[0]) for x in loaded_ims]
im_dim_list = torch.FloatTensor(im_dim_list).repeat(1,2)
leftover = 0
if (len(im_dim_list) % batch_size):
leftover = 1
if batch_size != 1:
num_batches = len(imlist) // batch_size + leftover
im_batches = [torch.cat((im_batches[i*batch_size : min((i + 1)*batch_size,
len(im_batches))])) for i in range(num_batches)]
write = 0
if CUDA:
im_dim_list = im_dim_list.cuda()
start_det_loop = time.time()
for i, batch in enumerate(im_batches):
start = time.time()
if CUDA:
batch = batch.cuda()
with torch.no_grad():
prediction = model(Variable(batch), CUDA)
prediction = write_results(prediction, confidence, num_classes, nms_conf = nms_thesh)
end = time.time()
if type(prediction) == int:
for im_num, image in enumerate(imlist[i*batch_size: min((i + 1)*batch_size, len(imlist))]):
im_id = i*batch_size + im_num
print("{0:20s} predicted in {1:6.3f} seconds".format(image.split("/")[-1], (end - start)/batch_size))
print("{0:20s} {1:s}".format("Objects Detected:", ""))
print("----------------------------------------------------------")
continue
prediction[:,0] += i*batch_size
if not write:
output = prediction
write = 1
else:
output = torch.cat((output,prediction))
for im_num, image in enumerate(imlist[i*batch_size: min((i + 1)*batch_size, len(imlist))]):
im_id = i*batch_size + im_num
objs = [classes[int(x[-1])] for x in output if int(x[0]) == im_id]
print("{0:20s} predicted in {1:6.3f} seconds".format(image.split("/")[-1], (end - start)/batch_size))
print("{0:20s} {1:s}".format("Objects Detected:", " ".join(objs)))
print("----------------------------------------------------------")
if CUDA:
torch.cuda.synchronize()
try:
output
except NameError:
print ("No detections were made")
exit()
im_dim_list = torch.index_select(im_dim_list, 0, output[:,0].long())
scaling_factor = torch.min(416/im_dim_list,1)[0].view(-1,1)
output[:,[1,3]] -= (inp_dim - scaling_factor*im_dim_list[:,0].view(-1,1))/2
output[:,[2,4]] -= (inp_dim - scaling_factor*im_dim_list[:,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_list[i,0])
output[i, [2,4]] = torch.clamp(output[i, [2,4]], 0.0, im_dim_list[i,1])
output_recast = time.time()
class_load = time.time()
colors = pkl.load(open("pallete", "rb"))
draw = time.time()
def write(x, results):
c1 = tuple(x[1:3].int())
c2 = tuple(x[3:5].int())
img = results[int(x[0])]
cls = int(x[-1])
color = random.choice(colors)
label = "{0}".format(classes[cls])
cv2.rectangle(img, c1, c2,color, 4)
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
list(map(lambda x: write(x, loaded_ims), output))
det_names = pd.Series(imlist).apply(lambda x: "{}/det_{}".format(args.det,x.split('\\')[-1]))
print(det_names[0])
list(map(cv2.imwrite, det_names, loaded_ims))
end = time.time()
print("SUMMARY")
print("----------------------------------------------------------")
print("{:25s}: {}".format("Task", "Time Taken (in seconds)"))
print()
print("{:25s}: {:2.3f}".format("Reading addresses", load_batch - read_dir))
print("{:25s}: {:2.3f}".format("Loading batch", start_det_loop - load_batch))
print("{:25s}: {:2.3f}".format("Detection (" + str(len(imlist)) + " images)", output_recast - start_det_loop))
print("{:25s}: {:2.3f}".format("Output Processing", class_load - output_recast))
print("{:25s}: {:2.3f}".format("Drawing Boxes", end - draw))
print("{:25s}: {:2.3f}".format("Average time_per_img", (end - load_batch)/len(imlist)))
print("----------------------------------------------------------")
torch.cuda.empty_cache()