forked from zylo117/Yet-Another-EfficientDet-Pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpred_jackson.py
108 lines (80 loc) · 3.93 KB
/
pred_jackson.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
# Author: Zylo117
"""
Simple Inference Script of EfficientDet-Pytorch
"""
import time
import os
import json
import torch
from torch.backends import cudnn
from matplotlib import colors
from backbone import EfficientDetBackbone
import cv2
import numpy as np
from efficientdet.utils import BBoxTransform, ClipBoxes
from utils.utils import preprocess, invert_affine, postprocess, STANDARD_COLORS, standard_to_bgr, get_index_label, plot_one_box
def to_json(out, out_dict):
cls = [int(c) for c in out[0]['class_ids']]
score = [float(s) for s in out[0]['scores']]
st = {'class': cls, 'score': score}
out_dict[len(out_dict)] = st
def main(i):
compound_coef = i
force_input_size = None # set None to use default size
# 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']
out_dict = dict()
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536, 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', map_location='cpu'))
model.requires_grad_(False)
model.eval()
if use_cuda:
model = model.cuda()
base_dir = '/data/jiashenc/jackson/'
print('Processing Det-' + str(i))
for k in range(1000000, 1100000):
if k % 1000 == 0:
print(' Finish {} frames'.format(k + 1))
img_path = os.path.join(base_dir, 'frame{}.jpg'.format(k))
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)
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)
to_json(out, out_dict)
with open(os.path.join(base_dir, '10', 'res-{:d}.json'.format(i)), 'w') as f:
json.dump(out_dict, f)
out_dict = dict()
if __name__ == '__main__':
for m in range(0, 8):
main(m)