forked from zylo117/Yet-Another-EfficientDet-Pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathefficientpose_test.py
147 lines (112 loc) · 5.23 KB
/
efficientpose_test.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
# # Author: Zylo117
# """
# Simple Inference Script of EfficientDet-Pytorch
# """
# import time,os
# import numpy as np
# from tqdm import tqdm
# import math
# import cv2
# import torch
# from torch.backends import cudnn
# from matplotlib import colors
# from backbone import EfficientPoseBackbone
# import cv2
# import numpy as np
# from efficientdet.utils import BBoxTransform, ClipBoxes
# from utils.utils import preprocess_det, invert_affine, postprocess_det, STANDARD_COLORS, standard_to_bgr, get_index_label, plot_one_box
# compound_coef = 0 # 耦合因子φ
# 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']
# color_list = standard_to_bgr(STANDARD_COLORS)
# # tf bilinear interpolation is different from any other's, just make do
# 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
# ori_imgs, framed_imgs, framed_metas = preprocess_det(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) #whc到CWH
# model = EfficientPoseBackbone(
# 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'), strict = False)
# 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_det(x,
# anchors, regression, classification,
# regressBoxes, clipBoxes,
# threshold, iou_threshold)
# def display(preds, imgs, imshow=True, imwrite=False):
# for i in range(len(imgs)):
# if len(preds[i]['rois']) == 0:
# continue
# imgs[i] = imgs[i].copy()
# for j in range(len(preds[i]['rois'])):
# x1, y1, x2, y2 = preds[i]['rois'][j].astype(int)
# obj = obj_list[preds[i]['class_ids'][j]]
# score = float(preds[i]['scores'][j])
# plot_one_box(imgs[i], [x1, y1, x2, y2], label=obj,score=score,color=color_list[get_index_label(obj, obj_list)])
# if imshow:
# cv2.imshow('img', imgs[i])
# cv2.waitKey(0)
# if imwrite:
# cv2.imwrite(f'test/img_inferred_d{compound_coef}_this_repo_{i}.jpg', imgs[i])
# out = invert_affine(framed_metas, out)
# display(out, ori_imgs, imshow=False, imwrite=True)
# print('running speed test...')
# with torch.no_grad():
# print('test1: model inferring and postprocess_deting')
# print('inferring image for 10 times...')
# t1 = time.time()
# for _ in range(10):
# _, regression, classification, anchors = model(x)
# out = postprocess_det(x,
# anchors, regression, classification,
# regressBoxes, clipBoxes,
# threshold, iou_threshold)
# out = invert_affine(framed_metas, out)
# t2 = time.time()
# tact_time = (t2 - t1) / 10
# print(f'{tact_time} seconds, {1 / tact_time} FPS, @batch_size 1')
# # uncomment this if you want a extreme fps test
# # print('test2: model inferring only')
# # print('inferring images for batch_size 32 for 10 times...')
# # t1 = time.time()
# # x = torch.cat([x] * 32, 0)
# # for _ in range(10):
# # _, regression, classification, anchors = model(x)
# #
# # t2 = time.time()
# # tact_time = (t2 - t1) / 10
# # print(f'{tact_time} seconds, {32 / tact_time} FPS, @batch_size 32')