File size: 3,437 Bytes
7734d5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from loguru import logger

import torch
import torch.backends.cudnn as cudnn

from yolox.core import Trainer, launch
from yolox.exp import get_exp

import argparse
import random
import warnings


def make_parser():
    parser = argparse.ArgumentParser("YOLOX train parser")
    parser.add_argument("-expn", "--experiment-name", type=str, default=None)
    parser.add_argument("-n", "--name", type=str, default=None, help="model name")

    # distributed
    parser.add_argument(
        "--dist-backend", default="nccl", type=str, help="distributed backend"
    )
    parser.add_argument(
        "--dist-url",
        default=None,
        type=str,
        help="url used to set up distributed training",
    )
    parser.add_argument("-b", "--batch-size", type=int, default=64, help="batch size")
    parser.add_argument(
        "-d", "--devices", default=None, type=int, help="device for training"
    )
    parser.add_argument(
        "--local_rank", default=0, type=int, help="local rank for dist training"
    )
    parser.add_argument(
        "-f",
        "--exp_file",
        default=None,
        type=str,
        help="plz input your expriment description file",
    )
    parser.add_argument(
        "--resume", default=False, action="store_true", help="resume training"
    )
    parser.add_argument("-c", "--ckpt", default=None, type=str, help="checkpoint file")
    parser.add_argument(
        "-e",
        "--start_epoch",
        default=None,
        type=int,
        help="resume training start epoch",
    )
    parser.add_argument(
        "--num_machines", default=1, type=int, help="num of node for training"
    )
    parser.add_argument(
        "--machine_rank", default=0, type=int, help="node rank for multi-node training"
    )
    parser.add_argument(
        "--fp16",
        dest="fp16",
        default=True,
        action="store_true",
        help="Adopting mix precision training.",
    )
    parser.add_argument(
        "-o",
        "--occupy",
        dest="occupy",
        default=False,
        action="store_true",
        help="occupy GPU memory first for training.",
    )
    parser.add_argument(
        "opts",
        help="Modify config options using the command-line",
        default=None,
        nargs=argparse.REMAINDER,
    )
    return parser


@logger.catch
def main(exp, args):
    if exp.seed is not None:
        random.seed(exp.seed)
        torch.manual_seed(exp.seed)
        cudnn.deterministic = True
        warnings.warn(
            "You have chosen to seed training. This will turn on the CUDNN deterministic setting, "
            "which can slow down your training considerably! You may see unexpected behavior "
            "when restarting from checkpoints."
        )

    # set environment variables for distributed training
    cudnn.benchmark = True

    trainer = Trainer(exp, args)
    trainer.train()


if __name__ == "__main__":
    args = make_parser().parse_args()
    exp = get_exp(args.exp_file, args.name)
    exp.merge(args.opts)

    if not args.experiment_name:
        args.experiment_name = exp.exp_name

    num_gpu = torch.cuda.device_count() if args.devices is None else args.devices
    assert num_gpu <= torch.cuda.device_count()

    launch(
        main,
        num_gpu,
        args.num_machines,
        args.machine_rank,
        backend=args.dist_backend,
        dist_url=args.dist_url,
        args=(exp, args),
    )