-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathfrcnn.py
238 lines (170 loc) · 8.89 KB
/
frcnn.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
import colorsys
import os
import time
import numpy as np
import torch
import torch.nn as nn
from PIL import Image, ImageDraw, ImageFont
from nets.frcnn import FasterRCNN
from utils.utils import (cvtColor, get_classes, get_new_img_size, resize_image,
preprocess_input, show_config)
from utils.utils_bbox import DecodeBox
class FRCNN(object):
_defaults = {
"model_path": 'model_data/voc_weights_resnet.pth',
"classes_path": 'model_data/voc_classes.txt',
"backbone": "resnet50",
"confidence": 0.5,
"nms_iou": 0.3,
'anchors_size': [8, 16, 32],
"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)
self.std = torch.Tensor([0.1, 0.1, 0.2, 0.2]).repeat(self.num_classes + 1)[None]
if self.cuda:
self.std = self.std.cuda()
self.bbox_util = DecodeBox(self.std, self.num_classes)
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):
self.net = FasterRCNN(self.num_classes, "predict", anchor_scales=self.anchors_size, backbone=self.backbone)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
self.net.load_state_dict(torch.load(self.model_path, map_location=device))
self.net = self.net.eval()
print('{} model, anchors, and classes loaded.'.format(self.model_path))
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])
input_shape = get_new_img_size(image_shape[0], image_shape[1])
image = cvtColor(image)
image_data = resize_image(image, [input_shape[1], input_shape[0]])
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()
roi_cls_locs, roi_scores, rois, _ = self.net(images)
results = self.bbox_util.forward(roi_cls_locs, roi_scores, rois, image_shape, input_shape,
nms_iou=self.nms_iou, confidence=self.confidence)
if len(results[0]) <= 0:
return image
top_label = np.array(results[0][:, 5], dtype='int32')
top_conf = results[0][:, 4]
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(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 get_FPS(self, image, test_interval):
image_shape = np.array(np.shape(image)[0:2])
input_shape = get_new_img_size(image_shape[0], image_shape[1])
image = cvtColor(image)
image_data = resize_image(image, [input_shape[1], input_shape[0]])
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()
roi_cls_locs, roi_scores, rois, _ = self.net(images)
results = self.bbox_util.forward(roi_cls_locs, roi_scores, rois, image_shape, input_shape,
nms_iou=self.nms_iou, confidence=self.confidence)
t1 = time.time()
for _ in range(test_interval):
with torch.no_grad():
roi_cls_locs, roi_scores, rois, _ = self.net(images)
results = self.bbox_util.forward(roi_cls_locs, roi_scores, rois, image_shape, input_shape,
nms_iou=self.nms_iou, confidence=self.confidence)
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
def get_map_txt(self, image_id, image, class_names, map_out_path):
f = open(os.path.join(map_out_path, "detection-results/" + image_id + ".txt"), "w")
image_shape = np.array(np.shape(image)[0:2])
input_shape = get_new_img_size(image_shape[0], image_shape[1])
image = cvtColor(image)
image_data = resize_image(image, [input_shape[1], input_shape[0]])
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()
roi_cls_locs, roi_scores, rois, _ = self.net(images)
results = self.bbox_util.forward(roi_cls_locs, roi_scores, rois, image_shape, input_shape,
nms_iou=self.nms_iou, confidence=self.confidence)
if len(results[0]) <= 0:
return
top_label = np.array(results[0][:, 5], dtype='int32')
top_conf = results[0][:, 4]
top_boxes = results[0][:, :4]
for i, c in list(enumerate(top_label)):
predicted_class = self.class_names[int(c)]
box = top_boxes[i]
score = str(top_conf[i])
top, left, bottom, right = box
if predicted_class not in class_names:
continue
f.write("%s %s %s %s %s %s\n" % (
predicted_class, score[:6], str(int(left)), str(int(top)), str(int(right)), str(int(bottom))))
f.close()
return