-
Notifications
You must be signed in to change notification settings - Fork 0
/
test_video.py
208 lines (174 loc) · 8 KB
/
test_video.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
# Run the code with below params
# python test_video.py -c model_data/obj.names -m yolov4_custom_weights_45000.h5 -a model_data/yolo4_anchors.txt
import os
import colorsys
import cv2
import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from yolo4.model import yolo_eval, yolo4_body
from yolo4.utils import letterbox_image
from PIL import Image, ImageFont, ImageDraw
from timeit import default_timer as timer
import matplotlib.pyplot as plt
import argparse
class Yolo4(object):
def get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def get_anchors(self):
anchors_path = os.path.expanduser(self.anchors_path)
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
return np.array(anchors).reshape(-1, 2)
def load_yolo(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
self.class_names = self.get_class()
self.anchors = self.get_anchors()
num_anchors = len(self.anchors)
num_classes = len(self.class_names)
# Generate colors for drawing bounding boxes.
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
self.sess = K.get_session()
# Load model, or construct model and load weights.
self.yolo4_model = yolo4_body(Input(shape=(416, 416, 3)), num_anchors//3, num_classes)
self.yolo4_model.load_weights(model_path)
print('{} model, anchors, and classes loaded.'.format(model_path))
if self.gpu_num>=2:
self.yolo4_model = multi_gpu_model(self.yolo4_model, gpus=self.gpu_num)
self.input_image_shape = K.placeholder(shape=(2, ))
self.boxes, self.scores, self.classes = yolo_eval(self.yolo4_model.output, self.anchors,
len(self.class_names), self.input_image_shape,
score_threshold=self.score)
def __init__(self, score, iou, anchors_path, classes_path, model_path, gpu_num=1):
self.score = score
self.iou = iou
self.anchors_path = anchors_path
self.classes_path = classes_path
self.model_path = model_path
self.gpu_num = gpu_num
self.load_yolo()
self.colors = np.random.uniform(0, 255, size=(len(self.class_names), 3))
def close_session(self):
self.sess.close()
def detect_image(self, image,cv2_img, model_image_size=(608, 608)):
start = timer()
boxed_image = letterbox_image(image, tuple(reversed(model_image_size)))
image_data = np.array(boxed_image, dtype='float32')
print(image_data.shape)
image_data /= 255.
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={
self.yolo4_model.input: image_data,
self.input_image_shape: [image.size[1], image.size[0]],
K.learning_phase(): 0
})
print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
# font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
# size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
# thickness = (image.size[0] + image.size[1]) // 300
# COLORS = np.random.uniform(0, 255, size=(len(self.class_names), 3)).astype('int32')
inf = timer()
print('INference Time:-',inf-start)
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
label = '{} {:.2f}'.format(predicted_class, score)
# draw = ImageDraw.Draw(image)
# label_size = draw.textsize(label, font)
label_size = cv2.getTextSize(label,cv2.FONT_HERSHEY_COMPLEX,0.5,2)
print(label_size)
top, left, bottom, right = box
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
# My kingdom for a good redistributable image drawing library.
# for i in range(thickness):
color = self.colors[c]
print(label, (left, top), (right, bottom),image.size[0],image.size[1])
cv2.rectangle(cv2_img, (left,top), (right,bottom),color, 2)
cv2.putText(cv2_img, label, tuple(text_origin), cv2.FONT_HERSHEY_SIMPLEX, 0.75, color, 2)
# draw.rectangle(
# [left + i, top + i, right - i, bottom - i],
# outline=self.colors[c])
# draw.rectangle(
# [tuple(text_origin), tuple(text_origin + label_size)],
# fill=self.colors[c])
# draw.text(text_origin, label, fill=(0, 0, 0), font=font)
# cv2.imshow('Detections',draw)
# del draw
end = timer()
print(end - start)
return cv2_img
if __name__ == '__main__':
ap = argparse.ArgumentParser()
ap.add_argument('-c','--classes_path',default = 'model_data/obj.names',required =True,help='Path to class names file')
ap.add_argument('-m','--model_path',default = 'yolov4_custom_weights_22000.h5',required =True,help='Path to model weights file')
ap.add_argument('-a','--anchors_path',default = 'model_data/yolo4_anchors.txt',required=True,help='anchors text path file')
# ap.add_argument('-w','--weights_path' ,default = 'yolov4-custom_22000.weights',required=True,help='weights path file')
args = vars(ap.parse_args())
model_path = args['model_path']
anchors_path = args['anchors_path']
# classes_path = 'model_data/coco_classes.txt'
classes_path = args['classes_path']
# model_path = 'yolo4_customweight.h5'
# anchors_path = 'model_data/yolo4_anchors.txt'
# classes_path = 'model_data/obj.names'
score = 0.3
iou = 0.4
model_image_size = (416, 416)
yolo4_model = Yolo4(score, iou, anchors_path, classes_path, model_path)
while True:
video_path = input('Input Video filename if camera type 0:')
if video_path == '0':
cap = cv2.VideoCapture(0)
break
else:
if os.path.exists(video_path):
cap = cv2.VideoCapture(video_path)
break
else:
print("Path doesn't exits")
plt.ion()
# fps = FPS().start()
count =0
while True:
_,image = cap.read()
image = cv2.cvtColor(image,cv2.COLOR_BGR2RGB)
cv2_img = image
image = Image.fromarray(image)
count+=1
if count%10 == 0:
print(count)
result = yolo4_model.detect_image(image,cv2_img, model_image_size=model_image_size)
result = cv2.cvtColor(result,cv2.COLOR_BGR2RGB)
cv2.imshow("object detection", cv2.resize(result,(700,600),interpolation=cv2.INTER_LANCZOS4))
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# plt.imshow(result)
# plt.pause(0.2)
# plt.show()
# plt.ioff()
# plt.show()
cap.release()
cv2.destroyAllWindows()
yolo4_model.close_session()