Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
analyze_logs.py 4.44 KB
Newer Older
chenzk's avatar
v1.0  
chenzk committed
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 
# Copyright (c) OpenMMLab. All rights reserved.
"""Modified from https://github.com/open-
mmlab/mmdetection/blob/master/tools/analysis_tools/analyze_logs.py."""
import argparse
import json
from collections import defaultdict

import matplotlib.pyplot as plt
import seaborn as sns


def plot_curve(log_dicts, args):
    if args.backend is not None:
        plt.switch_backend(args.backend)
    sns.set_style(args.style)
    # if legend is None, use {filename}_{key} as legend
    legend = args.legend
    if legend is None:
        legend = []
        for json_log in args.json_logs:
            for metric in args.keys:
                legend.append(f'{json_log}_{metric}')
    assert len(legend) == (len(args.json_logs) * len(args.keys))
    metrics = args.keys

    num_metrics = len(metrics)
    for i, log_dict in enumerate(log_dicts):
        epochs = list(log_dict.keys())
        for j, metric in enumerate(metrics):
            print(f'plot curve of {args.json_logs[i]}, metric is {metric}')
            plot_epochs = []
            plot_iters = []
            plot_values = []
            # In some log files, iters number is not correct, `pre_iter` is
            # used to prevent generate wrong lines.
            pre_iter = -1
            for epoch in epochs:
                epoch_logs = log_dict[epoch]
                if metric not in epoch_logs.keys():
                    continue
                if metric in ['mIoU', 'mAcc', 'aAcc']:
                    plot_epochs.append(epoch)
                    plot_values.append(epoch_logs[metric][0])
                else:
                    for idx in range(len(epoch_logs[metric])):
                        if pre_iter > epoch_logs['iter'][idx]:
                            continue
                        pre_iter = epoch_logs['iter'][idx]
                        plot_iters.append(epoch_logs['iter'][idx])
                        plot_values.append(epoch_logs[metric][idx])
            ax = plt.gca()
            label = legend[i * num_metrics + j]
            if metric in ['mIoU', 'mAcc', 'aAcc']:
                ax.set_xticks(plot_epochs)
                plt.xlabel('epoch')
                plt.plot(plot_epochs, plot_values, label=label, marker='o')
            else:
                plt.xlabel('iter')
                plt.plot(plot_iters, plot_values, label=label, linewidth=0.5)
        plt.legend()
        if args.title is not None:
            plt.title(args.title)
    if args.out is None:
        plt.show()
    else:
        print(f'save curve to: {args.out}')
        plt.savefig(args.out)
        plt.cla()


def parse_args():
    parser = argparse.ArgumentParser(description='Analyze Json Log')
    parser.add_argument(
        'json_logs',
        type=str,
        nargs='+',
        help='path of train log in json format')
    parser.add_argument(
        '--keys',
        type=str,
        nargs='+',
        default=['mIoU'],
        help='the metric that you want to plot')
    parser.add_argument('--title', type=str, help='title of figure')
    parser.add_argument(
        '--legend',
        type=str,
        nargs='+',
        default=None,
        help='legend of each plot')
    parser.add_argument(
        '--backend', type=str, default=None, help='backend of plt')
    parser.add_argument(
        '--style', type=str, default='dark', help='style of plt')
    parser.add_argument('--out', type=str, default=None)
    args = parser.parse_args()
    return args


def load_json_logs(json_logs):
    # load and convert json_logs to log_dict, key is epoch, value is a sub dict
    # keys of sub dict is different metrics
    # value of sub dict is a list of corresponding values of all iterations
    log_dicts = [dict() for _ in json_logs]
    for json_log, log_dict in zip(json_logs, log_dicts):
        with open(json_log, 'r') as log_file:
            for line in log_file:
                log = json.loads(line.strip())
                # skip lines without `epoch` field
                if 'epoch' not in log:
                    continue
                epoch = log.pop('epoch')
                if epoch not in log_dict:
                    log_dict[epoch] = defaultdict(list)
                for k, v in log.items():
                    log_dict[epoch][k].append(v)
    return log_dicts


def main():
    args = parse_args()
    json_logs = args.json_logs
    for json_log in json_logs:
        assert json_log.endswith('.json')
    log_dicts = load_json_logs(json_logs)
    plot_curve(log_dicts, args)


if __name__ == '__main__':
    main()