AndroidAIAutoController/eval.py at master · seamasZ/AndroidAIAutoController · GitHub

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
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

import os
import argparse

from glob import glob
from tqdm import tqdm
from multiprocessing import Pool
from toolkit.datasets import OTBDataset, UAVDataset, LaSOTDataset, \
        VOTDataset, NFSDataset, VOTLTDataset
from toolkit.evaluation import OPEBenchmark, AccuracyRobustnessBenchmark, \
        EAOBenchmark, F1Benchmark


#自己添加的
# import multiprocessing
# multiprocessing.set_start_method('spawn',True)

# python ../../tools/eval.py 	 \
# 	--tracker_path ./results \ # result path
# 	--dataset VOT2018        \ # dataset name
# 	--num 1 		 \             # number thread to eval
# 	--tracker_prefix 'model'   # tracker_name


def evaluation(dataset='VOT2018',tracker_prefix='DaSiamRPN',tracker_path='./results',num=4,show_video_level=False):


    tracker_dir = os.path.join(tracker_path,dataset)
    trackers = glob(os.path.join(tracker_path,
                                 dataset,
                                 tracker_prefix+'*'))
    trackers = [x.split('/')[-1] for x in trackers]

    assert len(trackers) > 0
    num = min(num, len(trackers))

    root = os.path.realpath(os.path.join(os.path.dirname(__file__),
                            '../datasets'))
    root = os.path.join(root, dataset)
    if 'OTB' in dataset:
        dataset = OTBDataset(dataset, root)
        dataset.set_tracker(tracker_dir, trackers)
        benchmark = OPEBenchmark(dataset)
        success_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_success,trackers), desc='eval success', total=len(trackers), ncols=100):
                success_ret.update(ret)
        precision_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_precision,
                trackers), desc='eval precision', total=len(trackers), ncols=100):
                precision_ret.update(ret)
        benchmark.show_result(success_ret, precision_ret,
                show_video_level=show_video_level)
    elif 'LaSOT' == dataset:
        dataset = LaSOTDataset(dataset, root)
        dataset.set_tracker(tracker_dir, trackers)
        benchmark = OPEBenchmark(dataset)
        success_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_success,
                trackers), desc='eval success', total=len(trackers), ncols=100):
                success_ret.update(ret)
        precision_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_precision,
                trackers), desc='eval precision', total=len(trackers), ncols=100):
                precision_ret.update(ret)
        norm_precision_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_norm_precision,
                trackers), desc='eval norm precision', total=len(trackers), ncols=100):
                norm_precision_ret.update(ret)
        benchmark.show_result(success_ret, precision_ret, norm_precision_ret,
                show_video_level=show_video_level)
    elif 'UAV' in dataset:
        dataset = UAVDataset(dataset, root)
        dataset.set_tracker(tracker_dir, trackers)
        benchmark = OPEBenchmark(dataset)
        success_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_success,
                trackers), desc='eval success', total=len(trackers), ncols=100):
                success_ret.update(ret)
        precision_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_precision,
                trackers), desc='eval precision', total=len(trackers), ncols=100):
                precision_ret.update(ret)
        benchmark.show_result(success_ret, precision_ret,
                show_video_level=show_video_level)
    elif 'NFS' in dataset:
        dataset = NFSDataset(dataset, root)
        dataset.set_tracker(tracker_dir, trackers)
        benchmark = OPEBenchmark(dataset)
        success_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_success,
                trackers), desc='eval success', total=len(trackers), ncols=100):
                success_ret.update(ret)
        precision_ret = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval_precision,
                trackers), desc='eval precision', total=len(trackers), ncols=100):
                precision_ret.update(ret)
        benchmark.show_result(success_ret, precision_ret,
                show_video_level=show_video_level)
    elif dataset in ['VOT2016', 'VOT2017', 'VOT2018', 'VOT2019']:
        dataset = VOTDataset(dataset, root)
        dataset.set_tracker(tracker_dir, trackers)
        ar_benchmark = AccuracyRobustnessBenchmark(dataset)
        ar_result = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(ar_benchmark.eval,
                trackers), desc='eval ar', total=len(trackers), ncols=100):
                ar_result.update(ret)

        benchmark = EAOBenchmark(dataset)
        eao_result = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval,
                trackers), desc='eval eao', total=len(trackers), ncols=100):
                eao_result.update(ret)
        ar_benchmark.show_result(ar_result, eao_result,
                show_video_level=show_video_level)
    elif 'VOT2018-LT' == dataset:
        dataset = VOTLTDataset(dataset, root)
        dataset.set_tracker(tracker_dir, trackers)
        benchmark = F1Benchmark(dataset)
        f1_result = {}
        with Pool(processes=num) as pool:
            for ret in tqdm(pool.imap_unordered(benchmark.eval,
                trackers), desc='eval f1', total=len(trackers), ncols=100):
                f1_result.update(ret)
        benchmark.show_result(f1_result,
                show_video_level=show_video_level)