-
Notifications
You must be signed in to change notification settings - Fork 58
/
yolo_tiny.py
207 lines (178 loc) · 8.91 KB
/
yolo_tiny.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
import numpy as np
import tensorflow as tf
import cv2
import time
class yolo_tf:
fromfile = None
tofile_img = 'test/output.jpg'
tofile_txt = 'test/output.txt'
imshow = True
filewrite_img = False
filewrite_txt = False
disp_console = True
result_box = None
weights_file = 'weights/YOLO_tiny.ckpt'
alpha = 0.1
threshold = 0.1
iou_threshold = 0.5
num_class = 20
num_box = 2
grid_size = 7
classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
def __init__(self):
self.build_networks()
def build_networks(self):
print("Building YOLO_tiny graph...")
self.x = tf.placeholder('float32', [None, 448, 448, 3])
self.conv_1 = self.conv_layer(1, self.x, 16, 3, 1)
self.pool_2 = self.pooling_layer(2, self.conv_1, 2, 2)
self.conv_3 = self.conv_layer(3, self.pool_2, 32, 3, 1)
self.pool_4 = self.pooling_layer(4, self.conv_3, 2, 2)
self.conv_5 = self.conv_layer(5, self.pool_4, 64, 3, 1)
self.pool_6 = self.pooling_layer(6, self.conv_5, 2, 2)
self.conv_7 = self.conv_layer(7, self.pool_6, 128, 3, 1)
self.pool_8 = self.pooling_layer(8, self.conv_7, 2, 2)
self.conv_9 = self.conv_layer(9, self.pool_8, 256, 3, 1)
self.pool_10 = self.pooling_layer(10, self.conv_9, 2, 2)
self.conv_11 = self.conv_layer(11, self.pool_10, 512, 3, 1)
self.pool_12 = self.pooling_layer(12, self.conv_11, 2, 2)
self.conv_13 = self.conv_layer(13, self.pool_12, 1024, 3, 1)
self.conv_14 = self.conv_layer(14, self.conv_13, 1024, 3, 1)
self.conv_15 = self.conv_layer(15, self.conv_14, 1024, 3, 1)
self.fc_16 = self.fc_layer(16, self.conv_15, 256, flat=True, linear=False)
self.fc_17 = self.fc_layer(17, self.fc_16, 4096, flat=False, linear=False)
# skip dropout_18
self.fc_19 = self.fc_layer(19, self.fc_17, 1470, flat=False, linear=True)
self.sess = tf.Session()
self.sess.run(tf.initialize_all_variables())
self.saver = tf.train.Saver()
self.saver.restore(self.sess, self.weights_file)
print("Loading complete!" + '\n')
def conv_layer(self, idx, inputs, filters, size, stride):
channels = inputs.get_shape()[3]
weight = tf.Variable(tf.truncated_normal([size, size, int(channels), filters], stddev=0.1))
biases = tf.Variable(tf.constant(0.1, shape=[filters]))
pad_size = size // 2
pad_mat = np.array([[0, 0], [pad_size, pad_size], [pad_size, pad_size], [0, 0]])
inputs_pad = tf.pad(inputs, pad_mat)
conv = tf.nn.conv2d(inputs_pad, weight, strides=[1, stride, stride, 1], padding='VALID',
name=str(idx) + '_conv')
conv_biased = tf.add(conv, biases, name=str(idx) + '_conv_biased')
print(' Layer %d : Type = Conv, Size = %d * %d, Stride = %d, Filters = %d, Input channels = %d' % (
idx, size, size, stride, filters, int(channels)))
return tf.maximum(self.alpha * conv_biased, conv_biased, name=str(idx) + '_leaky_relu')
def pooling_layer(self, idx, inputs, size, stride):
print(' Layer %d : Type = Pool, Size = %d * %d, Stride = %d' % (idx, size, size, stride))
return tf.nn.max_pool(inputs, ksize=[1, size, size, 1], strides=[1, stride, stride, 1], padding='SAME',
name=str(idx) + '_pool')
def fc_layer(self, idx, inputs, hiddens, flat=False, linear=False):
input_shape = inputs.get_shape().as_list()
if flat:
dim = input_shape[1] * input_shape[2] * input_shape[3]
inputs_transposed = tf.transpose(inputs, (0, 3, 1, 2))
inputs_processed = tf.reshape(inputs_transposed, [-1, dim])
else:
dim = input_shape[1]
inputs_processed = inputs
weight = tf.Variable(tf.truncated_normal([dim, hiddens], stddev=0.1))
biases = tf.Variable(tf.constant(0.1, shape=[hiddens]))
print(' Layer %d : Type = Full, Hidden = %d, Input dimension = %d, Flat = %d, Activation = %d' % (
idx, hiddens, int(dim), int(flat), 1 - int(linear)))
if linear: return tf.add(tf.matmul(inputs_processed, weight), biases, name=str(idx) + '_fc')
ip = tf.add(tf.matmul(inputs_processed, weight), biases)
return tf.maximum(self.alpha * ip, ip, name=str(idx) + '_fc')
def detect_from_crop_sample(self):
self.w_img = 640
self.h_img = 420
f = np.array(open('person_crop.txt', 'r').readlines(), dtype='float32')
inputs = np.zeros((1, 448, 448, 3), dtype='float32')
for c in range(3):
for y in range(448):
for x in range(448):
inputs[0, y, x, c] = f[c * 448 * 448 + y * 448 + x]
in_dict = {self.x: inputs}
net_output = self.sess.run(self.fc_19, feed_dict=in_dict)
self.boxes, self.probs = self.interpret_output(net_output[0])
img = cv2.imread('person.jpg')
self.show_results(self.boxes, img)
def detect_from_file(yolo,filename):
detect_from_cvmat(yolo, filename)
def detect_from_cvmat(yolo,img):
s = time.time()
yolo.h_img, yolo.w_img, _ = img.shape
img_resized = cv2.resize(img, (448, 448))
img_RGB = cv2.cvtColor(img_resized, cv2.COLOR_BGR2RGB)
img_resized_np = np.asarray(img_RGB)
inputs = np.zeros((1, 448, 448, 3), dtype='float32')
inputs[0] = (img_resized_np / 255.0) * 2.0 - 1.0
in_dict = {yolo.x: inputs}
net_output = yolo.sess.run(yolo.fc_19, feed_dict=in_dict)
result = interpret_output(yolo, net_output[0])
yolo.result_box = result
strtime = str(time.time() - s)
print('Elapsed time : ' + strtime + ' secs' + '\n')
def detect_from_file(yolo,filename):
detect_from_cvmat(yolo, filename)
def interpret_output(yolo, output):
probs = np.zeros((7, 7, 2, 20))
class_probs = np.reshape(output[0:980], (7, 7, 20))
scales = np.reshape(output[980:1078], (7, 7, 2))
boxes = np.reshape(output[1078:], (7, 7, 2, 4))
offset = np.transpose(np.reshape(np.array([np.arange(7)] * 14), (2, 7, 7)), (1, 2, 0))
boxes[:, :, :, 0] += offset
boxes[:, :, :, 1] += np.transpose(offset, (1, 0, 2))
boxes[:, :, :, 0:2] = boxes[:, :, :, 0:2] / 7.0
boxes[:, :, :, 2] = np.multiply(boxes[:, :, :, 2], boxes[:, :, :, 2])
boxes[:, :, :, 3] = np.multiply(boxes[:, :, :, 3], boxes[:, :, :, 3])
boxes[:, :, :, 0] *= yolo.w_img
boxes[:, :, :, 1] *= yolo.h_img
boxes[:, :, :, 2] *= yolo.w_img
boxes[:, :, :, 3] *= yolo.h_img
for i in range(2):
for j in range(20):
probs[:, :, i, j] = np.multiply(class_probs[:, :, j], scales[:, :, i])
filter_mat_probs = np.array(probs >= yolo.threshold, dtype='bool')
filter_mat_boxes = np.nonzero(filter_mat_probs)
boxes_filtered = boxes[filter_mat_boxes[0], filter_mat_boxes[1], filter_mat_boxes[2]]
probs_filtered = probs[filter_mat_probs]
classes_num_filtered = np.argmax(filter_mat_probs, axis=3)[
filter_mat_boxes[0], filter_mat_boxes[1], filter_mat_boxes[2]]
argsort = np.array(np.argsort(probs_filtered))[::-1]
boxes_filtered = boxes_filtered[argsort]
probs_filtered = probs_filtered[argsort]
classes_num_filtered = classes_num_filtered[argsort]
for i in range(len(boxes_filtered)):
if probs_filtered[i] == 0: continue
for j in range(i + 1, len(boxes_filtered)):
if iou(boxes_filtered[i], boxes_filtered[j]) > yolo.iou_threshold:
probs_filtered[j] = 0.0
filter_iou = np.array(probs_filtered > 0.0, dtype='bool')
boxes_filtered = boxes_filtered[filter_iou]
probs_filtered = probs_filtered[filter_iou]
classes_num_filtered = classes_num_filtered[filter_iou]
result = []
for i in range(len(boxes_filtered)):
result.append(
[yolo.classes[classes_num_filtered[i]], boxes_filtered[i][0], boxes_filtered[i][1], boxes_filtered[i][2],
boxes_filtered[i][3], probs_filtered[i]])
return result
def show_results(img,yolo):
img_cp = img.copy()
results = yolo.result_box
rect_box = np.zeros_like(img_cp)
for i in range(len(results)):
x = int(results[i][1])
y = int(results[i][2])
w = int(results[i][3])//2
h = int(results[i][4])//2
cv2.rectangle(rect_box, (x - w, y - h), (x + w, y + h), (125, 125, 125), 10)
cv2.rectangle(rect_box,(x-w,y-h),(x+w,y+h),(255,125,0),-1)
img_cp = cv2.addWeighted(img_cp, 1, rect_box, 0.3, 0)
return img_cp
def iou(box1,box2):
tb = min(box1[0]+0.5*box1[2],box2[0]+0.5*box2[2])-max(box1[0]-0.5*box1[2],box2[0]-0.5*box2[2])
lr = min(box1[1]+0.5*box1[3],box2[1]+0.5*box2[3])-max(box1[1]-0.5*box1[3],box2[1]-0.5*box2[3])
if tb < 0 or lr < 0 : intersection = 0
else : intersection = tb*lr
return intersection / (box1[2]*box1[3] + box2[2]*box2[3] - intersection)