-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathunet.py
202 lines (172 loc) · 8.97 KB
/
unet.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
import colorsys
import copy
import time
import cv2
import numpy as np
import torch
import torch.nn.functional as F
from PIL import Image
from torch import nn
from nets.unet import Unet as unet
from utils.utils import cvtColor, preprocess_input, resize_image, show_config
class Unet(object):
_defaults = {
"model_path": 'model_data/unet_vgg_voc.pth',
"num_classes": 21,
"backbone": "vgg",
"input_shape": [512, 512],
"mix_type": 0,
"cuda": True,
}
def __init__(self, **kwargs):
self.__dict__.update(self._defaults)
for name, value in kwargs.items():
setattr(self, name, value)
if self.num_classes <= 21:
self.colors = [(0, 0, 0), (128, 0, 0), (0, 128, 0), (128, 128, 0), (0, 0, 128), (128, 0, 128),
(0, 128, 128),
(128, 128, 128), (64, 0, 0), (192, 0, 0), (64, 128, 0), (192, 128, 0), (64, 0, 128),
(192, 0, 128),
(64, 128, 128), (192, 128, 128), (0, 64, 0), (128, 64, 0), (0, 192, 0), (128, 192, 0),
(0, 64, 128),
(128, 64, 12)]
else:
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 = unet(num_classes=self.num_classes, 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, 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, count=False, name_classes=None):
image = cvtColor(image)
old_img = copy.deepcopy(image)
orininal_h = np.array(image).shape[0]
orininal_w = np.array(image).shape[1]
image_data, nw, nh = resize_image(image, (self.input_shape[1], self.input_shape[0]))
image_data = np.expand_dims(np.transpose(preprocess_input(np.array(image_data, np.float32)), (2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.cuda()
pr = self.net(images)[0]
pr = F.softmax(pr.permute(1, 2, 0), dim=-1).cpu().numpy()
pr = pr[int((self.input_shape[0] - nh) // 2): int((self.input_shape[0] - nh) // 2 + nh), \
int((self.input_shape[1] - nw) // 2): int((self.input_shape[1] - nw) // 2 + nw)]
pr = cv2.resize(pr, (orininal_w, orininal_h), interpolation=cv2.INTER_LINEAR)
pr = pr.argmax(axis=-1)
if count:
classes_nums = np.zeros([self.num_classes])
total_points_num = orininal_h * orininal_w
print('-' * 63)
print("|%25s | %15s | %15s|" % ("Key", "Value", "Ratio"))
print('-' * 63)
for i in range(self.num_classes):
num = np.sum(pr == i)
ratio = num / total_points_num * 100
if num > 0:
print("|%25s | %15s | %14.2f%%|" % (str(name_classes[i]), str(num), ratio))
print('-' * 63)
classes_nums[i] = num
print("classes_nums:", classes_nums)
if self.mix_type == 0:
# seg_img = np.zeros((np.shape(pr)[0], np.shape(pr)[1], 3))
# for c in range(self.num_classes):
# seg_img[:, :, 0] += ((pr[:, :] == c ) * self.colors[c][0]).astype('uint8')
# seg_img[:, :, 1] += ((pr[:, :] == c ) * self.colors[c][1]).astype('uint8')
# seg_img[:, :, 2] += ((pr[:, :] == c ) * self.colors[c][2]).astype('uint8')
seg_img = np.reshape(np.array(self.colors, np.uint8)[np.reshape(pr, [-1])], [orininal_h, orininal_w, -1])
image = Image.fromarray(np.uint8(seg_img))
image = Image.blend(old_img, image, 0.7)
elif self.mix_type == 1:
# seg_img = np.zeros((np.shape(pr)[0], np.shape(pr)[1], 3))
# for c in range(self.num_classes):
# seg_img[:, :, 0] += ((pr[:, :] == c ) * self.colors[c][0]).astype('uint8')
# seg_img[:, :, 1] += ((pr[:, :] == c ) * self.colors[c][1]).astype('uint8')
# seg_img[:, :, 2] += ((pr[:, :] == c ) * self.colors[c][2]).astype('uint8')
seg_img = np.reshape(np.array(self.colors, np.uint8)[np.reshape(pr, [-1])], [orininal_h, orininal_w, -1])
image = Image.fromarray(np.uint8(seg_img))
elif self.mix_type == 2:
seg_img = (np.expand_dims(pr != 0, -1) * np.array(old_img, np.float32)).astype('uint8')
image = Image.fromarray(np.uint8(seg_img))
return image
def get_FPS(self, image, test_interval):
image = cvtColor(image)
image_data, nw, nh = resize_image(image, (self.input_shape[1], self.input_shape[0]))
image_data = np.expand_dims(np.transpose(preprocess_input(np.array(image_data, np.float32)), (2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.cuda()
pr = self.net(images)[0]
pr = F.softmax(pr.permute(1, 2, 0), dim=-1).cpu().numpy().argmax(axis=-1)
pr = pr[int((self.input_shape[0] - nh) // 2): int((self.input_shape[0] - nh) // 2 + nh), \
int((self.input_shape[1] - nw) // 2): int((self.input_shape[1] - nw) // 2 + nw)]
t1 = time.time()
for _ in range(test_interval):
with torch.no_grad():
pr = self.net(images)[0]
pr = F.softmax(pr.permute(1, 2, 0), dim=-1).cpu().numpy().argmax(axis=-1)
pr = pr[int((self.input_shape[0] - nh) // 2): int((self.input_shape[0] - nh) // 2 + nh), \
int((self.input_shape[1] - nw) // 2): int((self.input_shape[1] - nw) // 2 + nw)]
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
def convert_to_onnx(self, simplify, model_path):
import onnx
self.generate(onnx=True)
im = torch.zeros(1, 3, *self.input_shape).to('cpu') # image size(1, 3, 512, 512) BCHW
input_layer_names = ["images"]
output_layer_names = ["output"]
# Export the model
print(f'Starting export with onnx {onnx.__version__}.')
torch.onnx.export(self.net,
im,
f=model_path,
verbose=False,
opset_version=12,
training=torch.onnx.TrainingMode.EVAL,
do_constant_folding=True,
input_names=input_layer_names,
output_names=output_layer_names,
dynamic_axes=None)
# Checks
model_onnx = onnx.load(model_path) # load onnx model
onnx.checker.check_model(model_onnx) # check onnx model
# Simplify onnx
if simplify:
import onnxsim
print(f'Simplifying with onnx-simplifier {onnxsim.__version__}.')
model_onnx, check = onnxsim.simplify(
model_onnx,
dynamic_input_shape=False,
input_shapes=None)
assert check, 'assert check failed'
onnx.save(model_onnx, model_path)
print('Onnx model save as {}'.format(model_path))
def get_miou_png(self, image):
image = cvtColor(image)
orininal_h = np.array(image).shape[0]
orininal_w = np.array(image).shape[1]
image_data, nw, nh = resize_image(image, (self.input_shape[1], self.input_shape[0]))
image_data = np.expand_dims(np.transpose(preprocess_input(np.array(image_data, np.float32)), (2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.cuda()
pr = self.net(images)[0]
pr = F.softmax(pr.permute(1, 2, 0), dim=-1).cpu().numpy()
pr = pr[int((self.input_shape[0] - nh) // 2): int((self.input_shape[0] - nh) // 2 + nh), \
int((self.input_shape[1] - nw) // 2): int((self.input_shape[1] - nw) // 2 + nw)]
pr = cv2.resize(pr, (orininal_w, orininal_h), interpolation=cv2.INTER_LINEAR)
pr = pr.argmax(axis=-1)
image = Image.fromarray(np.uint8(pr))
return image