-
Notifications
You must be signed in to change notification settings - Fork 0
/
yolo.py
303 lines (242 loc) · 12.8 KB
/
yolo.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
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
import colorsys
import os
import time
import numpy as np
import torch
import torch.nn as nn
from PIL import ImageDraw, ImageFont
import cv2
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from PIL import Image
from nets.yolo import YoloBody
from utils.utils import (cvtColor, get_classes, preprocess_input, resize_image,
show_config)
from utils.utils_bbox import decode_outputs, non_max_suppression
'''
训练自己的数据集必看注释！
'''
class YOLO(object):
_defaults = {
# --------------------------------------------------------------------------#
# 使用自己训练好的模型进行预测一定要修改model_path和classes_path！
# model_path指向logs文件夹下的权值文件，classes_path指向model_data下的txt
#
# 训练好后logs文件夹下存在多个权值文件，选择验证集损失较低的即可。
# 验证集损失较低不代表mAP较高，仅代表该权值在验证集上泛化性能较好。
# 如果出现shape不匹配，同时要注意训练时的model_path和classes_path参数的修改
# --------------------------------------------------------------------------#
"model_path": '/data/newnas/zhangHY/ToothData661s/s_model_logs/best_epoch_weights.pth',
"classes_path": 'model_data/voc_classes.txt',
# ---------------------------------------------------------------------#
# 输入图片的大小，必须为32的倍数。
# ---------------------------------------------------------------------#
"input_shape": [640, 640],
# ---------------------------------------------------------------------#
# 所使用的YoloX的版本。nano、tiny、s、m、l、x
# ---------------------------------------------------------------------#
"phi": 's',
# ---------------------------------------------------------------------#
# 只有得分大于置信度的预测框会被保留下来
# ---------------------------------------------------------------------#
"confidence": 0.5,
# ---------------------------------------------------------------------#
# 非极大抑制所用到的nms_iou大小
# ---------------------------------------------------------------------#
"nms_iou": 0.3,
# ---------------------------------------------------------------------#
# 该变量用于控制是否使用letterbox_image对输入图像进行不失真的resize，
# 在多次测试后，发现关闭letterbox_image直接resize的效果更好
# ---------------------------------------------------------------------#
"letterbox_image": True,
# -------------------------------#
# 是否使用Cuda
# 没有GPU可以设置成False
# -------------------------------#
"cuda": True,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
def __init__(self, **kwargs):
self.__dict__.update(self._defaults)
for name, value in kwargs.items():
setattr(self, name, value)
self._defaults[name] = value
self.class_names, self.num_classes = get_classes(self.classes_path)
hsv_tuples = [(x / self.num_classes, 1., 1.) for x in range(self.num_classes)]
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.generate()
show_config(**self._defaults)
def generate(self, onnx=False):
self.net = YoloBody(self.num_classes, self.phi)
self.net.to(self.device)
# device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
self.net.load_state_dict(torch.load(self.model_path, map_location=self.device))
self.net = self.net.eval()
print('{} model, and classes loaded.'.format(self.model_path))
if not onnx:
if self.cuda:
self.net = nn.DataParallel(self.net)
self.net = self.net.cuda()
def detect_image(self, image, crop=False, count=False):
image_shape = np.array(np.shape(image)[0:2])
image = cvtColor(image)
image_data = resize_image(image, (self.input_shape[1], self.input_shape[0]), self.letterbox_image)
image_data = np.expand_dims(np.transpose(preprocess_input(np.array(image_data, dtype='float32')), (2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.to(self.device)
outputs = self.net(images)
outputs = decode_outputs(outputs, self.input_shape)
results = non_max_suppression(outputs, self.num_classes, self.input_shape,
image_shape, self.letterbox_image, conf_thres=self.confidence,
nms_thres=self.nms_iou)
if results[0] is None:
return image
top_label = np.array(results[0][:, 6], dtype='int32')
top_conf = results[0][:, 4] * results[0][:, 5]
top_boxes = results[0][:, :4]
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
thickness = int(max((image.size[0] + image.size[1]) // np.mean(self.input_shape), 1))
if count:
print("top_label:", top_label)
classes_nums = np.zeros([self.num_classes])
for i in range(self.num_classes):
num = np.sum(top_label == i)
if num > 0:
print(self.class_names[i], " : ", num)
classes_nums[i] = num
print("classes_nums:", classes_nums)
if crop:
for i, c in list(enumerate(top_label)):
top, left, bottom, right = top_boxes[i]
top = max(0, np.floor(top).astype('int32'))
left = max(0, np.floor(left).astype('int32'))
bottom = min(image.size[1], np.floor(bottom).astype('int32'))
right = min(image.size[0], np.floor(right).astype('int32'))
dir_save_path = "img_crop"
if not os.path.exists(dir_save_path):
os.makedirs(dir_save_path)
crop_image = image.crop([left, top, right, bottom])
crop_image.save(os.path.join(dir_save_path, "crop_" + str(i) + ".png"), quality=95, subsampling=0)
print("save crop_" + str(i) + ".png to " + dir_save_path)
for i, c in list(enumerate(top_label)):
predicted_class = self.class_names[int(c)]
box = top_boxes[i]
score = top_conf[i]
top, left, bottom, right = box
top = max(0, np.floor(top).astype('int32'))
left = max(0, np.floor(left).astype('int32'))
bottom = min(image.size[1], np.floor(bottom).astype('int32'))
right = min(image.size[0], np.floor(right).astype('int32'))
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label, top, left, bottom, right)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
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, str(label, 'UTF-8'), fill=(0, 0, 0), font=font)
del draw
return image
def detect_bbox(self, image, crop=False, count=False):
image_shape = np.array(np.shape(image)[0:2])
image = cvtColor(image)
image_data = resize_image(image, (self.input_shape[1], self.input_shape[0]), self.letterbox_image)
image_data = np.expand_dims(np.transpose(preprocess_input(np.array(image_data, dtype='float32')), (2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.cuda()
outputs = self.net(images)
outputs = decode_outputs(outputs, self.input_shape)
results = non_max_suppression(outputs, self.num_classes, self.input_shape,
image_shape, self.letterbox_image, conf_thres=self.confidence,
nms_thres=self.nms_iou)
if results[0] is None:
return []
top_label = np.array(results[0][:, 6], dtype='int32')
top_conf = results[0][:, 4] * results[0][:, 5]
top_boxes = results[0][:, :4]
if count:
print("top_label:", top_label)
classes_nums = np.zeros([self.num_classes])
for i in range(self.num_classes):
num = np.sum(top_label == i)
if num > 0:
print(self.class_names[i], " : ", num)
classes_nums[i] = num
print("classes_nums:", classes_nums)
if crop:
for i, c in list(enumerate(top_label)):
top, left, bottom, right = top_boxes[i]
top = max(0, np.floor(top).astype('int32'))
left = max(0, np.floor(left).astype('int32'))
bottom = min(image.size[1], np.floor(bottom).astype('int32'))
right = min(image.size[0], np.floor(right).astype('int32'))
dir_save_path = "img_crop"
if not os.path.exists(dir_save_path):
os.makedirs(dir_save_path)
crop_image = image.crop([left, top, right, bottom])
crop_image.save(os.path.join(dir_save_path, "crop_" + str(i) + ".png"), quality=95, subsampling=0)
print("save crop_" + str(i) + ".png to " + dir_save_path)
bbox_list = []
for i, c in list(enumerate(top_label)):
predicted_class = self.class_names[int(c)]
box = top_boxes[i]
score = top_conf[i]
top, left, bottom, right = box
top = max(0, np.floor(top).astype('int32'))
left = max(0, np.floor(left).astype('int32'))
bottom = min(image.size[1], np.floor(bottom).astype('int32'))
right = min(image.size[0], np.floor(right).astype('int32'))
bbox_list.append([top, left, bottom, right, predicted_class, score])
return bbox_list
def detect_heatmap(self, image, heatmap_save_path):
import cv2
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
def sigmoid(x):
y = 1.0 / (1.0 + np.exp(-x))
return y
image_shape = np.array(np.shape(image)[0:2])
image = cvtColor(image)
image_data = resize_image(image, (self.input_shape[1], self.input_shape[0]), self.letterbox_image)
image_data = np.expand_dims(np.transpose(preprocess_input(np.array(image_data, dtype='float32')), (2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.cuda()
outputs = self.net(images)
outputs = [output.cpu().numpy() for output in outputs]
plt.imshow(image, alpha=1)
plt.axis('off')
mask = np.zeros((image.size[1], image.size[0]))
for sub_output in outputs:
b, c, h, w = np.shape(sub_output)
sub_output = np.transpose(sub_output, [0, 2, 3, 1])[0]
score = np.max(sigmoid(sub_output[..., 5:]), -1) * sigmoid(sub_output[..., 4])
score = cv2.resize(score, (image.size[0], image.size[1]))
normed_score = (score * 255).astype('uint8')
mask = np.maximum(mask, normed_score)
plt.imshow(mask, alpha=0.5, interpolation='nearest', cmap="jet")
plt.axis('off')
plt.subplots_adjust(top=1, bottom=0, right=1, left=0, hspace=0, wspace=0)
plt.margins(0, 0)
plt.savefig(heatmap_save_path, dpi=200)
print("Save to the " + heatmap_save_path)
plt.cla()