video_test.py
4.18 KB
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
from __future__ import division, print_function
import tensorflow as tf
import numpy as np
import argparse
import cv2
import time
from misc_utils import parse_anchors, read_class_names
from nms_utils import gpu_nms
from plot_utils import get_color_table, plot_one_box
from data_utils import letterbox_resize
from model import yolov3
parser = argparse.ArgumentParser(description="YOLO-V3 video test procedure.")
parser.add_argument("input_video", type=str,
help="The path of the input video.")
parser.add_argument("--anchor_path", type=str, default="./data/yolo_anchors.txt",
help="The path of the anchor txt file.")
parser.add_argument("--new_size", nargs='*', type=int, default=[416, 416],
help="Resize the input image with `new_size`, size format: [width, height]")
parser.add_argument("--letterbox_resize", type=lambda x: (str(x).lower() == 'true'), default=True,
help="Whether to use the letterbox resize.")
parser.add_argument("--class_name_path", type=str, default="./data/classes.txt",
help="The path of the class names.")
parser.add_argument("--restore_path", type=str, default="./data/darknet_weights/yolov3.ckpt",
help="The path of the weights to restore.")
parser.add_argument("--save_video", type=lambda x: (str(x).lower() == 'true'), default=False,
help="Whether to save the video detection results.")
args = parser.parse_args()
args.anchors = parse_anchors(args.anchor_path)
args.classes = read_class_names(args.class_name_path)
args.num_class = len(args.classes)
color_table = get_color_table(args.num_class)
vid = cv2.VideoCapture(args.input_video)
video_frame_cnt = int(vid.get(7))
video_width = int(vid.get(3))
video_height = int(vid.get(4))
video_fps = int(vid.get(5))
if args.save_video:
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
videoWriter = cv2.VideoWriter('video_result.mp4', fourcc, video_fps, (video_width, video_height))
with tf.Session() as sess:
input_data = tf.placeholder(tf.float32, [1, args.new_size[1], args.new_size[0], 3], name='input_data')
yolo_model = yolov3(args.num_class, args.anchors)
with tf.variable_scope('yolov3'):
pred_feature_maps = yolo_model.forward(input_data, False)
pred_boxes, pred_confs, pred_probs = yolo_model.predict(pred_feature_maps)
pred_scores = pred_confs * pred_probs
boxes, scores, labels = gpu_nms(pred_boxes, pred_scores, args.num_class, max_boxes=200, score_thresh=0.3, nms_thresh=0.45)
saver = tf.train.Saver()
saver.restore(sess, args.restore_path)
for i in range(video_frame_cnt):
ret, img_ori = vid.read()
if args.letterbox_resize:
img, resize_ratio, dw, dh = letterbox_resize(img_ori, args.new_size[0], args.new_size[1])
else:
height_ori, width_ori = img_ori.shape[:2]
img = cv2.resize(img_ori, tuple(args.new_size))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = np.asarray(img, np.float32)
img = img[np.newaxis, :] / 255.
start_time = time.time()
boxes_, scores_, labels_ = sess.run([boxes, scores, labels], feed_dict={input_data: img})
end_time = time.time()
# rescale the coordinates to the original image
if args.letterbox_resize:
boxes_[:, [0, 2]] = (boxes_[:, [0, 2]] - dw) / resize_ratio
boxes_[:, [1, 3]] = (boxes_[:, [1, 3]] - dh) / resize_ratio
else:
boxes_[:, [0, 2]] *= (width_ori/float(args.new_size[0]))
boxes_[:, [1, 3]] *= (height_ori/float(args.new_size[1]))
for i in range(len(boxes_)):
x0, y0, x1, y1 = boxes_[i]
plot_one_box(img_ori, [x0, y0, x1, y1], label=args.classes[labels_[i]] + ', {:.2f}%'.format(scores_[i] * 100), color=color_table[labels_[i]])
cv2.putText(img_ori, '{:.2f}ms'.format((end_time - start_time) * 1000), (40, 40), 0,
fontScale=1, color=(0, 255, 0), thickness=2)
cv2.imshow('image', img_ori)
if args.save_video:
videoWriter.write(img_ori)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
vid.release()
if args.save_video:
videoWriter.release()