forked from markgao-916/yolov3_fire_detection
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdataset.py
executable file
·288 lines (222 loc) · 12.3 KB
/
dataset.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
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
#! /usr/bin/env python
# coding=utf-8
#================================================================
# Copyright (C) 2019 * Ltd. All rights reserved.
#
# Editor : VIM
# File name : dataset.py
# Author : YunYang1994
# Created date: 2019-03-15 18:05:03
# Description :
#
#================================================================
import os
import cv2
import random
import numpy as np
import tensorflow as tf
import core.utils as utils
from core.config import cfg
import utiles.autoAugment_utils as autoAug
class Dataset(object):
"""implement Dataset here"""
def __init__(self, dataset_type):
self.annot_path = cfg.TRAIN.ANNOT_PATH if dataset_type == 'train' else cfg.TEST.ANNOT_PATH
self.input_sizes = cfg.TRAIN.INPUT_SIZE if dataset_type == 'train' else cfg.TEST.INPUT_SIZE
self.batch_size = cfg.TRAIN.BATCH_SIZE if dataset_type == 'train' else cfg.TEST.BATCH_SIZE
self.data_aug = cfg.TRAIN.DATA_AUG if dataset_type == 'train' else cfg.TEST.DATA_AUG
self.train_input_sizes = cfg.TRAIN.INPUT_SIZE
self.strides = np.array(cfg.YOLO.STRIDES)
self.classes = utils.read_class_names(cfg.YOLO.CLASSES)
self.num_classes = len(self.classes)
self.anchors = np.array(utils.get_anchors(cfg.YOLO.ANCHORS))
self.anchor_per_scale = cfg.YOLO.ANCHOR_PER_SCALE
self.max_bbox_per_scale = 150
self.annotations = self.load_annotations(dataset_type)
self.num_samples = len(self.annotations)
self.num_batchs = int(np.ceil(self.num_samples / self.batch_size))
self.batch_count = 0
gpu_options = tf.GPUOptions(visible_device_list='')
config = tf.ConfigProto(gpu_options=gpu_options)
self.sess = tf.Session(config=config)
self.aug_fun = self.augGraph(self.sess)
def augGraph(self, sess):
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3], name='img_plac')
box_plac = tf.placeholder(dtype=tf.float32, shape=[None, 4], name='box_plac')
img_aug, box_aug = autoAug.distort_image_with_autoaugment(img_plac, box_plac, 'v1')
sess.run(tf.global_variables_initializer())
return lambda img, box: sess.run([img_aug, box_aug], feed_dict={img_plac: img,
box_plac: box})
def load_annotations(self, dataset_type):
with open(self.annot_path, 'r') as f:
txt = f.readlines()
annotations = [line.strip() for line in txt if len(line.strip().split()[1:]) != 0]
np.random.shuffle(annotations)
return annotations
def __iter__(self):
return self
def __next__(self):
with tf.device('/cpu:0'):
self.train_input_size = random.choice(self.train_input_sizes)
self.train_output_sizes = self.train_input_size // self.strides
batch_image = np.zeros((self.batch_size, self.train_input_size, self.train_input_size, 3))
batch_label_sbbox = np.zeros((self.batch_size, self.train_output_sizes[0], self.train_output_sizes[0],
self.anchor_per_scale, 5 + self.num_classes))
batch_label_mbbox = np.zeros((self.batch_size, self.train_output_sizes[1], self.train_output_sizes[1],
self.anchor_per_scale, 5 + self.num_classes))
batch_label_lbbox = np.zeros((self.batch_size, self.train_output_sizes[2], self.train_output_sizes[2],
self.anchor_per_scale, 5 + self.num_classes))
batch_sbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4))
batch_mbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4))
batch_lbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4))
num = 0
if self.batch_count < self.num_batchs:
while num < self.batch_size:
index = self.batch_count * self.batch_size + num
if index >= self.num_samples: index -= self.num_samples
annotation = self.annotations[index]
image, bboxes = self.parse_annotation(annotation)
label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes = self.preprocess_true_boxes(bboxes)
batch_image[num, :, :, :] = image
batch_label_sbbox[num, :, :, :, :] = label_sbbox
batch_label_mbbox[num, :, :, :, :] = label_mbbox
batch_label_lbbox[num, :, :, :, :] = label_lbbox
batch_sbboxes[num, :, :] = sbboxes
batch_mbboxes[num, :, :] = mbboxes
batch_lbboxes[num, :, :] = lbboxes
num += 1
self.batch_count += 1
return batch_image, batch_label_sbbox, batch_label_mbbox, batch_label_lbbox, \
batch_sbboxes, batch_mbboxes, batch_lbboxes
else:
self.batch_count = 0
np.random.shuffle(self.annotations)
raise StopIteration
def random_horizontal_flip(self, image, bboxes):
if random.random() < 0.5:
_, w, _ = image.shape
image = image[:, ::-1, :]
bboxes[:, [0,2]] = w - bboxes[:, [2,0]]
return image, bboxes
def random_crop(self, image, bboxes):
if random.random() < 0.5:
h, w, _ = image.shape
max_bbox = np.concatenate([np.min(bboxes[:, 0:2], axis=0), np.max(bboxes[:, 2:4], axis=0)], axis=-1)
max_l_trans = max_bbox[0]
max_u_trans = max_bbox[1]
max_r_trans = w - max_bbox[2]
max_d_trans = h - max_bbox[3]
crop_xmin = max(0, int(max_bbox[0] - random.uniform(0, max_l_trans)))
crop_ymin = max(0, int(max_bbox[1] - random.uniform(0, max_u_trans)))
crop_xmax = max(w, int(max_bbox[2] + random.uniform(0, max_r_trans)))
crop_ymax = max(h, int(max_bbox[3] + random.uniform(0, max_d_trans)))
image = image[crop_ymin : crop_ymax, crop_xmin : crop_xmax]
bboxes[:, [0, 2]] = bboxes[:, [0, 2]] - crop_xmin
bboxes[:, [1, 3]] = bboxes[:, [1, 3]] - crop_ymin
return image, bboxes
def random_translate(self, image, bboxes):
if random.random() < 0.5:
h, w, _ = image.shape
max_bbox = np.concatenate([np.min(bboxes[:, 0:2], axis=0), np.max(bboxes[:, 2:4], axis=0)], axis=-1)
max_l_trans = max_bbox[0]
max_u_trans = max_bbox[1]
max_r_trans = w - max_bbox[2]
max_d_trans = h - max_bbox[3]
tx = random.uniform(-(max_l_trans - 1), (max_r_trans - 1))
ty = random.uniform(-(max_u_trans - 1), (max_d_trans - 1))
M = np.array([[1, 0, tx], [0, 1, ty]])
image = cv2.warpAffine(image, M, (w, h))
bboxes[:, [0, 2]] = bboxes[:, [0, 2]] + tx
bboxes[:, [1, 3]] = bboxes[:, [1, 3]] + ty
return image, bboxes
def parse_annotation(self, annotation):
line = annotation.split()
image_path = line[0]
if not os.path.exists(image_path):
raise KeyError("%s does not exist ... " %image_path)
image = np.array(cv2.imread(image_path))
bboxes = np.array([list(map(int, box.split(','))) for box in line[1:]])
bboxes = np.reshape(bboxes, [-1, 5])
if self.data_aug and random.random() < 0.9:
# image, bboxes = self.random_horizontal_flip(np.copy(image), np.copy(bboxes))
# image, bboxes = self.random_crop(np.copy(image), np.copy(bboxes))
# image, bboxes = self.random_translate(np.copy(image), np.copy(bboxes))
h, w, c = image.shape
scale = np.array([w, h, w, h], dtype=np.float64)
bboxes_aug = bboxes[:, :4]
bboxes_aug = bboxes_aug / scale
bboxes_aug = bboxes_aug[:, [1, 0, 3, 2]]
image, bboxes_aug = self.aug_fun(image, bboxes_aug)
bboxes_aug = bboxes_aug[:, [1, 0, 3, 2]]
h, w, c = image.shape
scale = np.array([w, h, w, h], dtype=np.float64)
bboxes_aug = bboxes_aug * scale
bboxes[:, :4] = bboxes_aug
image, bboxes = utils.image_preporcess(np.copy(image), [self.train_input_size, self.train_input_size], np.copy(bboxes))
return image, bboxes
def bbox_iou(self, boxes1, boxes2):
boxes1 = np.array(boxes1)
boxes2 = np.array(boxes2)
boxes1_area = boxes1[..., 2] * boxes1[..., 3]
boxes2_area = boxes2[..., 2] * boxes2[..., 3]
boxes1 = np.concatenate([boxes1[..., :2] - boxes1[..., 2:] * 0.5,
boxes1[..., :2] + boxes1[..., 2:] * 0.5], axis=-1)
boxes2 = np.concatenate([boxes2[..., :2] - boxes2[..., 2:] * 0.5,
boxes2[..., :2] + boxes2[..., 2:] * 0.5], axis=-1)
left_up = np.maximum(boxes1[..., :2], boxes2[..., :2])
right_down = np.minimum(boxes1[..., 2:], boxes2[..., 2:])
inter_section = np.maximum(right_down - left_up, 0.0)
inter_area = inter_section[..., 0] * inter_section[..., 1]
union_area = boxes1_area + boxes2_area - inter_area
return inter_area / union_area
def preprocess_true_boxes(self, bboxes):
label = [np.zeros((self.train_output_sizes[i], self.train_output_sizes[i], self.anchor_per_scale,
5 + self.num_classes)) for i in range(3)]
bboxes_xywh = [np.zeros((self.max_bbox_per_scale, 4)) for _ in range(3)]
bbox_count = np.zeros((3,))
for bbox in bboxes:
bbox_coor = bbox[:4]
bbox_class_ind = bbox[4]
onehot = np.zeros(self.num_classes, dtype=np.float)
onehot[bbox_class_ind] = 1.0
uniform_distribution = np.full(self.num_classes, 1.0 / self.num_classes)
deta = 0.01
smooth_onehot = onehot * (1 - deta) + deta * uniform_distribution
bbox_xywh = np.concatenate([(bbox_coor[2:] + bbox_coor[:2]) * 0.5, bbox_coor[2:] - bbox_coor[:2]], axis=-1)
bbox_xywh_scaled = 1.0 * bbox_xywh[np.newaxis, :] / self.strides[:, np.newaxis]
iou = []
exist_positive = False
for i in range(3):
anchors_xywh = np.zeros((self.anchor_per_scale, 4))
anchors_xywh[:, 0:2] = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32) + 0.5
anchors_xywh[:, 2:4] = self.anchors[i]
iou_scale = self.bbox_iou(bbox_xywh_scaled[i][np.newaxis, :], anchors_xywh)
iou.append(iou_scale)
iou_mask = iou_scale > 0.3
if np.any(iou_mask):
xind, yind = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32)
label[i][yind, xind, iou_mask, :] = 0
label[i][yind, xind, iou_mask, 0:4] = bbox_xywh
label[i][yind, xind, iou_mask, 4:5] = 1.0
label[i][yind, xind, iou_mask, 5:] = smooth_onehot
bbox_ind = int(bbox_count[i] % self.max_bbox_per_scale)
bboxes_xywh[i][bbox_ind, :4] = bbox_xywh
bbox_count[i] += 1
exist_positive = True
if not exist_positive:
best_anchor_ind = np.argmax(np.array(iou).reshape(-1), axis=-1)
best_detect = int(best_anchor_ind / self.anchor_per_scale)
best_anchor = int(best_anchor_ind % self.anchor_per_scale)
xind, yind = np.floor(bbox_xywh_scaled[best_detect, 0:2]).astype(np.int32)
label[best_detect][yind, xind, best_anchor, :] = 0
label[best_detect][yind, xind, best_anchor, 0:4] = bbox_xywh
label[best_detect][yind, xind, best_anchor, 4:5] = 1.0
label[best_detect][yind, xind, best_anchor, 5:] = smooth_onehot
bbox_ind = int(bbox_count[best_detect] % self.max_bbox_per_scale)
bboxes_xywh[best_detect][bbox_ind, :4] = bbox_xywh
bbox_count[best_detect] += 1
label_sbbox, label_mbbox, label_lbbox = label
sbboxes, mbboxes, lbboxes = bboxes_xywh
return label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes
def __len__(self):
return self.num_batchs