compare_results.py 4.25 KB
Newer Older
LDOUBLEV's avatar
LDOUBLEV committed
1
2
3
4
5
import numpy as np
import os
import subprocess
import json
import argparse
LDOUBLEV's avatar
LDOUBLEV committed
6
import glob
LDOUBLEV's avatar
LDOUBLEV committed
7
8
9
10


def init_args():
    parser = argparse.ArgumentParser()
LDOUBLEV's avatar
LDOUBLEV committed
11
    # params for testing assert allclose
LDOUBLEV's avatar
LDOUBLEV committed
12
13
14
15
    parser.add_argument("--atol", type=float, default=1e-3)
    parser.add_argument("--rtol", type=float, default=1e-3)
    parser.add_argument("--gt_file", type=str, default="")
    parser.add_argument("--log_file", type=str, default="")
LDOUBLEV's avatar
LDOUBLEV committed
16
    parser.add_argument("--precision", type=str, default="fp32")
LDOUBLEV's avatar
LDOUBLEV committed
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
    return parser


def parse_args():
    parser = init_args()
    return parser.parse_args()


def run_shell_command(cmd):
    p = subprocess.Popen(
        cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
    out, err = p.communicate()

    if p.returncode == 0:
        return out.decode('utf-8')
    else:
        return None

LDOUBLEV's avatar
rename  
LDOUBLEV committed
35

LDOUBLEV's avatar
LDOUBLEV committed
36
37
38
39
40
41
42
43
44
45
46
47
48
def parser_results_from_log_by_name(log_path, names_list):
    if not os.path.exists(log_path):
        raise ValueError("The log file {} does not exists!".format(log_path))

    if names_list is None or len(names_list) < 1:
        return []

    parser_results = {}
    for name in names_list:
        cmd = "grep {} {}".format(name, log_path)
        outs = run_shell_command(cmd)
        outs = outs.split("\n")[0]
        result = outs.split("{}".format(name))[-1]
49
50
51
52
        try:
            result = json.loads(result)
        except:
            result = np.array([int(r) for r in result.split()]).reshape(-1, 4)
LDOUBLEV's avatar
LDOUBLEV committed
53
54
55
        parser_results[name] = result
    return parser_results

LDOUBLEV's avatar
rename  
LDOUBLEV committed
56

LDOUBLEV's avatar
LDOUBLEV committed
57
58
59
60
61
62
63
64
65
def load_gt_from_file(gt_file):
    if not os.path.exists(gt_file):
        raise ValueError("The log file {} does not exists!".format(gt_file))
    with open(gt_file, 'r') as f:
        data = f.readlines()
        f.close()
    parser_gt = {}
    for line in data:
        image_name, result = line.strip("\n").split("\t")
66
67
68
69
70
        image_name = image_name.split('/')[-1]
        try:
            result = json.loads(result)
        except:
            result = np.array([int(r) for r in result.split()]).reshape(-1, 4)
LDOUBLEV's avatar
LDOUBLEV committed
71
72
73
74
        parser_gt[image_name] = result
    return parser_gt


LDOUBLEV's avatar
LDOUBLEV committed
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
def load_gt_from_txts(gt_file):
    gt_list = glob.glob(gt_file)
    gt_collection = {}
    for gt_f in gt_list:
        gt_dict = load_gt_from_file(gt_f)
        basename = os.path.basename(gt_f)
        if "fp32" in basename:
            gt_collection["fp32"] = [gt_dict, gt_f]
        elif "fp16" in basename:
            gt_collection["fp16"] = [gt_dict, gt_f]
        elif "int8" in basename:
            gt_collection["int8"] = [gt_dict, gt_f]
        else:
            continue
    return gt_collection


def collect_predict_from_logs(log_path, key_list):
    log_list = glob.glob(log_path)
    pred_collection = {}
    for log_f in log_list:
        pred_dict = parser_results_from_log_by_name(log_f, key_list)
        key = os.path.basename(log_f)
        pred_collection[key] = pred_dict

    return pred_collection


LDOUBLEV's avatar
LDOUBLEV committed
103
104
105
106
107
108
109
110
def testing_assert_allclose(dict_x, dict_y, atol=1e-7, rtol=1e-7):
    for k in dict_x:
        np.testing.assert_allclose(
            np.array(dict_x[k]), np.array(dict_y[k]), atol=atol, rtol=rtol)


if __name__ == "__main__":
    # Usage:
LDOUBLEV's avatar
LDOUBLEV committed
111
    # python3.7 tests/compare_results.py --gt_file=./tests/results/*.txt  --log_file=./tests/output/infer_*.log
LDOUBLEV's avatar
LDOUBLEV committed
112
113
114

    args = parse_args()

LDOUBLEV's avatar
LDOUBLEV committed
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
    gt_collection = load_gt_from_txts(args.gt_file)
    key_list = gt_collection["fp32"][0].keys()

    pred_collection = collect_predict_from_logs(args.log_file, key_list)
    for filename in pred_collection.keys():
        if "fp32" in filename:
            gt_dict, gt_filename = gt_collection["fp32"]
        elif "fp16" in filename:
            gt_dict, gt_filename = gt_collection["fp16"]
        elif "int8" in filename:
            gt_dict, gt_filename = gt_collection["int8"]
        else:
            continue
        pred_dict = pred_collection[filename]

        try:
            testing_assert_allclose(
                gt_dict, pred_dict, atol=args.atol, rtol=args.rtol)
            print(
                "Assert allclose passed! The results of {} and {} are consistent!".
                format(filename, gt_filename))
        except Exception as E:
            print(E)
            raise ValueError(
                "The results of {} and the results of {} are inconsistent!".
                format(filename, gt_filename))