tools/train.py

# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import logging
import os
import os.path as osp

from mmengine.config import Config, DictAction
from mmengine.logging import print_log
from mmengine.runner import Runner

from mmseg.registry import RUNNERS

import torch
import json
import numpy as np

def initialize_model_stitching_layer(model, data_loader):
    print(data_loader)
    # print(next(iter(data_loader)))
    dataiter = iter(data_loader)
    images = []
    total_samples = 50
    batch_size = data_loader.batch_size
    num_iter = total_samples // batch_size
    for i in range(num_iter):
        item = next(dataiter)
        images.append(item['img'].data[0])
    images = torch.cat(images, dim=0)
    samples = images.to(model.device, non_blocking=True)
    model.backbone.initialize_stitching_weights(samples)

def group_subnets_by_flops(data, flops_step=10):
    sorted_data = {k: v for k, v in sorted(data.items(), key=lambda item: item[1])}
    candidate_idx = []
    grouped_cands = []
    last_flops = 0
    for cfg_id, flops in sorted_data.items():
        # flops, _ = values
        flops = flops // 1e9
        if abs(last_flops - flops) > flops_step:
            if len(candidate_idx) > 0:
                grouped_cands.append(candidate_idx)
            candidate_idx = [int(cfg_id)]
            last_flops = flops
        else:
            candidate_idx.append(int(cfg_id))

    if len(candidate_idx) > 0:
        grouped_cands.append(candidate_idx)

    return grouped_cands

def parse_args():
    parser = argparse.ArgumentParser(description='Train a segmentor')
    parser.add_argument('config', help='train config file path')
    parser.add_argument('--work-dir', help='the dir to save logs and models')
    parser.add_argument(
        '--resume',
        action='store_true',
        default=False,
        help='resume from the latest checkpoint in the work_dir automatically')
    parser.add_argument(
        '--amp',
        action='store_true',
        default=False,
        help='enable automatic-mixed-precision training')
    parser.add_argument(
        '--cfg-options',
        nargs='+',
        action=DictAction,
        help='override some settings in the used config, the key-value pair '
        'in xxx=yyy format will be merged into config file. If the value to '
        'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
        'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
        'Note that the quotation marks are necessary and that no white space '
        'is allowed.')
    parser.add_argument(
        '--launcher',
        choices=['none', 'pytorch', 'slurm', 'mpi'],
        default='none',
        help='job launcher')
    # When using PyTorch version >= 2.0.0, the `torch.distributed.launch`
    # will pass the `--local-rank` parameter to `tools/train.py` instead
    # of `--local_rank`.
    parser.add_argument('--local_rank', '--local-rank', type=int, default=0)
    args = parser.parse_args()
    if 'LOCAL_RANK' not in os.environ:
        os.environ['LOCAL_RANK'] = str(args.local_rank)

    return args


def main():
    args = parse_args()

    # load config
    cfg = Config.fromfile(args.config)
    cfg.launcher = args.launcher
    if args.cfg_options is not None:
        cfg.merge_from_dict(args.cfg_options)

    # work_dir is determined in this priority: CLI > segment in file > filename
    if args.work_dir is not None:
        # update configs according to CLI args if args.work_dir is not None
        cfg.work_dir = args.work_dir
    elif cfg.get('work_dir', None) is None:
        # use config filename as default work_dir if cfg.work_dir is None
        cfg.work_dir = osp.join('./work_dirs',
                                osp.splitext(osp.basename(args.config))[0])

    # enable automatic-mixed-precision training
    if args.amp is True:
        optim_wrapper = cfg.optim_wrapper.type
        if optim_wrapper == 'AmpOptimWrapper':
            print_log(
                'AMP training is already enabled in your config.',
                logger='current',
                level=logging.WARNING)
        else:
            assert optim_wrapper == 'OptimWrapper', (
                '`--amp` is only supported when the optimizer wrapper type is '
                f'`OptimWrapper` but got {optim_wrapper}.')
            cfg.optim_wrapper.type = 'AmpOptimWrapper'
            cfg.optim_wrapper.loss_scale = 'dynamic'

    # resume training
    cfg.resume = args.resume

    # build the runner from config
    if 'runner_type' not in cfg:
        # build the default runner
        runner = Runner.from_cfg(cfg)
    else:
        # build customized runner from the registry
        # if 'runner_type' is set in the cfg
        runner = RUNNERS.build(cfg)

    # start training
    runner.train()


if __name__ == '__main__':
    main()