-
Notifications
You must be signed in to change notification settings - Fork 89
/
propagation.py
177 lines (150 loc) · 7.34 KB
/
propagation.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
from config import Input_shape, channels, threshold, ignore_thresh
from network_function import YOLOv3
from detect_function import predict
from utils.yolo_utils import read_anchors, read_classes, letterbox_image, resize_image
# from argparse import ArgumentParser
from pathlib import Path
from timeit import time
from timeit import default_timer as timer # to calculate FPS
from PIL import Image, ImageFont, ImageDraw
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
import colorsys
import random
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
from tensorflow.python.client import device_lib
print(device_lib.list_local_devices())
class YOLO(object):
def __init__(self):
self.anchors_path = './model_data/yolo_anchors.txt'
self.classes_path = './model_data/coco_classes.txt'
self.class_names = read_classes(self.classes_path)
self.anchors = read_anchors(self.anchors_path)
self.threshold = threshold
self.ignore_thresh = ignore_thresh
self.INPUT_SIZE = (Input_shape, Input_shape) # fixed size or (None, None)
self.is_fixed_size = self.INPUT_SIZE != (None, None)
def detect_image(self, image):
start = time.time()
# 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))
random.seed(10101) # Fixed seed for consistent colors across runs.
random.shuffle(self.colors) # Shuffle colors to decorrelate adjacent classes.
random.seed(None) # Reset seed to default.
if self.is_fixed_size:
assert self.INPUT_SIZE[0] % 32 == 0, 'Multiples of 32 required'
assert self.INPUT_SIZE[1] % 32 == 0, 'Multiples of 32 required'
boxed_image, image_shape = letterbox_image(image, tuple(reversed(self.INPUT_SIZE)))
# boxed_image, image_shape = resize_image(image, tuple(reversed(self.INPUT_SIZE)))
else:
new_image_size = (image.width - (image.width % 32), image.height - (image.height % 32))
boxed_image, image_shape = letterbox_image(image, new_image_size)
# boxed_image, image_shape = resize_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
print("heights, widths:", image_shape)
image_data /= 255.
inputs = np.expand_dims(image_data, 0) # Add batch dimension. #
# Generate output tensor targets for filtered bounding boxes.
x = tf.placeholder(tf.float32, shape=[None, Input_shape, Input_shape, channels])
# image_shape = np.array([image.size[0], image.size[1]]) # tf.placeholder(tf.float32, shape=[2,])
# Generate output tensor targets for filtered bounding boxes.
scale1, scale2, scale3 = YOLOv3(x, len(self.class_names)).feature_extractor()
scale_total = [scale1, scale2, scale3]
# detect
boxes, scores, classes = predict(scale_total, self.anchors, len(self.class_names), image_shape,
score_threshold=self.threshold, iou_threshold=self.ignore_thresh)
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
writer = tf.summary.FileWriter('./graphs', tf.get_default_graph())
# tensorboard --logdir="./graphs" --port 6006
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
# Restore variables from disk.
epoch = input('Entrer a check point at epoch(%10=0):')
checkpoint = "/home/minh/stage/saver_model/model" + str(epoch) + ".ckpt"
try:
my_abs_path = Path(checkpoint).resolve()
saver.restore(sess, checkpoint)
except FileNotFoundError:
print("Not yet training!")
else:
print("already training!")
out_boxes, out_scores, out_classes = sess.run([boxes, scores, classes], feed_dict={x: inputs})
writer.close()
print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
# Visualisation#################################################################################################
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]) // 400 # do day cua BB
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)
top, left, bottom, right = box # y_min, x_min, y_max, x_max
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'))
print(label, (left, top), (right, bottom)) # (x_min, y_min), (x_max, y_max)
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 j in range(thickness):
draw.rectangle([left + j, top + j, right - j, bottom - j], 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)
del draw
end = time.time()
print(end - start)
return image
def detect_video(yolo, video_path):
import cv2
vid = cv2.VideoCapture(video_path)
# if not vid.isOpened():
# raise IOError("Couldn't open webcam or video")
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
while True:
return_value, frame = vid.read()
image = Image.fromarray(frame)
image = yolo.detect_image(image)
result = np.asarray(image)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", result)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def detect_img(yolo):
while True:
img = input('Input image filename:')
try:
image = Image.open(img)
except:
print('Open Error! Try again!')
continue
else:
r_image = yolo.detect_image(image)
r_image.show()
if __name__ == '__main__':
detect_img(YOLO())
# detect_video(YOLO(), 'video.mp4')