-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcamear.py
107 lines (81 loc) · 3.99 KB
/
camear.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
import torch
from torch.backends import cudnn
from backbone import EfficientDetBackbone
import cv2
import numpy as np
from efficientdet.utils import BBoxTransform, ClipBoxes
from utils.utils import preprocess, invert_affine, postprocess,aspectaware_resize_padding
compound_coef = 0
force_input_size = None # set None to use default size
img_path = 'test/img.png'
# replace this part with your project's anchor config
anchor_ratios = [(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]
anchor_scales = [2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)]
threshold = 0.2
iou_threshold = 0.2
use_cuda = True
use_float16 = False
cudnn.fastest = True
cudnn.benchmark = True
obj_list = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
'fire hydrant', '', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
'cow', 'elephant', 'bear', 'zebra', 'giraffe', '', 'backpack', 'umbrella', '', '', 'handbag', 'tie',
'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove',
'skateboard', 'surfboard', 'tennis racket', 'bottle', '', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut',
'cake', 'chair', 'couch', 'potted plant', 'bed', '', 'dining table', '', '', 'toilet', '', 'tv',
'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', '', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier',
'toothbrush']
def preprocess1(img , max_size=512, mean=(0.406, 0.456, 0.485), std=(0.225, 0.224, 0.229)):
ori_imgs = [img]
normalized_imgs = [(img / 255 - mean) / std for img in ori_imgs]
imgs_meta = [aspectaware_resize_padding(img[..., ::-1], max_size, max_size,
means=None) for img in normalized_imgs]
framed_imgs = [img_meta[0] for img_meta in imgs_meta]
framed_metas = [img_meta[1:] for img_meta in imgs_meta]
return ori_imgs, framed_imgs, framed_metas
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
model = EfficientDetBackbone(compound_coef=compound_coef, num_classes=len(obj_list),
ratios=anchor_ratios, scales=anchor_scales)
model.load_state_dict(torch.load(f'weights/efficientdet-d{compound_coef}.pth'))
model.requires_grad_(False)
model.eval()
if use_cuda:
model = model.cuda()
if use_float16:
model = model.half()
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, 512)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 512)
ok, frame = cap.read()
while ok:
ori_imgs, framed_imgs, framed_metas = preprocess1(frame, 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)
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
for j in range(len(out[i]['rois'])):
(x1, y1, x2, y2) = out[i]['rois'][j].astype(np.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])
cv2.putText(ori_imgs[i], '{}, {:.3f}'.format(obj, score),
(x1, y1 + 10), cv2.FONT_HERSHEY_SIMPLEX, 1,
(255, 255, 0), 1)
cv2.imshow('img', ori_imgs[i])
key = cv2.waitKey(1) & 0xFF
ok, frame = cap.read()