forked from zylo117/Yet-Another-EfficientDet-Pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
/
eval_letters.py
144 lines (123 loc) · 3.09 KB
/
eval_letters.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
import torch
from torch.backends import cudnn
from backbone import EfficientDetBackbone
import cv2
import matplotlib.pyplot as plt
import numpy as np
from efficientdet.utils import BBoxTransform, ClipBoxes
from utils.utils import preprocess, invert_affine, postprocess
compound_coef = 0
force_input_size = None # set None to use default size
img_path = "datasets/letters/val/8020.jpg"
weight_file = "weights/letters_D0/efficientdet-d0_54_13700.pth"
# img_path = "datasets/letters_large/val/21039.jpg" # 21019 21024
# weight_file = "weights/letters_large_D0/efficientdet-d0_53_35400.pth"
threshold = 0.2
iou_threshold = 0.2
use_cuda = True
use_float16 = False
cudnn.fastest = True
cudnn.benchmark = True
obj_list = [
"0",
"1",
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
".",
",",
"-",
"A",
"B",
"C",
"D",
"E",
"F",
"G",
"H",
"I",
"J",
"K",
"L",
"M",
"N",
"O",
"P",
"Q",
"R",
"S",
"T",
"U",
"V",
"W",
"X",
"Y",
"Z",
]
# tf bilinear interpolation is different from any other's, just make do
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536]
input_size = (
input_sizes[compound_coef] if force_input_size is None else force_input_size
)
ori_imgs, framed_imgs, framed_metas = preprocess(img_path, max_size=input_size)
if use_cuda:
x = torch.stack([torch.from_numpy(fi).cuda() for fi in framed_imgs], 0)
else:
x = torch.stack([torch.from_numpy(fi) for fi in framed_imgs], 0)
x = x.to(torch.float32 if not use_float16 else torch.float16).permute(0, 3, 1, 2)
model = EfficientDetBackbone(
compound_coef=compound_coef,
num_classes=len(obj_list),
# replace this part with your project's anchor config
ratios=[(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)],
scales=[2**0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)],
)
model.load_state_dict(torch.load(weight_file))
model.requires_grad_(False)
model.eval()
if use_cuda:
model = model.cuda()
if use_float16:
model = model.half()
with torch.no_grad():
features, regression, classification, anchors = model(x)
regressBoxes = BBoxTransform()
clipBoxes = ClipBoxes()
out = postprocess(
x,
anchors,
regression,
classification,
regressBoxes,
clipBoxes,
threshold,
iou_threshold,
)
out = invert_affine(framed_metas, out)
for i in range(len(ori_imgs)):
if len(out[i]["rois"]) == 0:
continue
ori_imgs[i] = ori_imgs[i].copy()
for j in range(len(out[i]["rois"])):
(x1, y1, x2, y2) = out[i]["rois"][j].astype(int)
cv2.rectangle(ori_imgs[i], (x1, y1), (x2, y2), (255, 255, 0), 2)
obj = obj_list[out[i]["class_ids"][j]]
score = float(out[i]["scores"][j])
if score < 0.9:
continue
print(obj, x1, y1, x2, y2, score)
cv2.putText(
ori_imgs[i],
"{}, {:.3f}".format(obj, score),
(x1, y1 + 10),
cv2.FONT_HERSHEY_SIMPLEX,
0.5,
(255, 255, 0),
1,
)
plt.imshow(ori_imgs[i])