# Copyright (c) OpenMMLab. All rights reserved. import argparse import copy import os import os.path as osp import time import warnings import shutil import sys path = os.path.dirname(os.path.dirname(__file__)) print(path) sys.path.append("/home/kaijie-tang/userdata/qizhi/code_test") #os.environ['RANK'] = "0" #os.environ['WORLD_SIZE'] = "8" #os.environ['MASTER_ADDR'] = "localhost" #os.environ['MASTER_PORT'] = "1234" import mmcv import torch #os.environ["CUDA_VISIBLE_DEVICES"] = "0, 1, 2, 3" from mmcv import Config, DictAction from mmcv.runner import get_dist_info, init_dist from mmcv.utils import get_git_hash from pycocotools.coco import COCO from mmdet import __version__ from mmdet.apis import init_random_seed, set_random_seed, train_detector from mmdet.datasets import build_dataset from mmdet.models import build_detector from mmdet.utils import collect_env, get_root_logger def parse_args(): parser = argparse.ArgumentParser(description='Train a detector') parser.add_argument('--config', default='/home/kaijie-tang/userdata/qizhi/code_test/configs/AD_mlops/AD_mlops_test18.py', help='train config file path') parser.add_argument('--work-dir',default='/home/kaijie-tang/outputs/', help='the dir to save logs and models') parser.add_argument( '--resume-from', help='the checkpoint file to resume from') parser.add_argument( '--no-validate', action='store_true', help='whether not to evaluate the checkpoint during training') group_gpus = parser.add_mutually_exclusive_group() group_gpus.add_argument( '--gpus', type=int, help='number of gpus to use ' '(only applicable to non-distributed training)') group_gpus.add_argument( '--gpu-ids', type=int, nargs='+', help='ids of gpus to use ' '(only applicable to non-distributed training)') parser.add_argument('--seed', type=int, default=None, help='random seed') parser.add_argument( '--deterministic', action='store_true', help='whether to set deterministic options for CUDNN backend.') parser.add_argument( '--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 (deprecate), ' 'change to --cfg-options instead.') 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') parser.add_argument('--local_rank', type=int, default=0) parser.add_argument( '--data-path', default='/home/kaijie-tang/adhub/coco2017_train/0.1', help='dataset path') parser.add_argument( '--batchsize', type=int, default=8, help='training batch size') parser.add_argument( '--epoch', type=int, default=5, help='training epoch') parser.add_argument( '--warmup_iters', type=int, default=500, help='training warmup_iters') parser.add_argument( '--lr', type=float, default=0.001, help='learning rate') parser.add_argument('--train_image_size', type=list, default=[(100, 100)], help='train image size') parser.add_argument('--test_image_size', type=list, default=[(100, 100)], help='test image size') args = parser.parse_args() if 'LOCAL_RANK' not in os.environ: os.environ['LOCAL_RANK'] = str(args.local_rank) if args.options and args.cfg_options: raise ValueError( '--options and --cfg-options cannot be both ' 'specified, --options is deprecated in favor of --cfg-options') if args.options: warnings.warn('--options is deprecated in favor of --cfg-options') args.cfg_options = args.options return args def main(): args = parse_args() cfg = Config.fromfile(args.config) if args.cfg_options is not None: cfg.merge_from_dict(args.cfg_options) # import modules from string list. if cfg.get('custom_imports', None): from mmcv.utils import import_modules_from_strings import_modules_from_strings(**cfg['custom_imports']) # set cudnn_benchmark if cfg.get('cudnn_benchmark', False): torch.backends.cudnn.benchmark = True if args.batchsize is not None: cfg.data.samples_per_gpu = args.batchsize if args.epoch is not None: cfg.runner.max_epochs = args.epoch if args.warmup_iters is not None: cfg.lr_config.warmup_iters = args.warmup_iters if args.lr is not None: cfg.optimizer.lr = args.lr '''if args.train_image_size is not None: cfg.train_pipeline[2].img_scale = args.train_image_size cfg.data.train.dataset.pipeline[2].img_scale = args.train_image_size''' if args.test_image_size is not None: cfg.test_pipeline[1].img_scale = args.test_image_size cfg.data.val.pipeline[1].img_scale = args.test_image_size cfg.data.test.pipeline[1].img_scale = args.test_image_size #if on platform, change the classnum fit the user define dataset if args.data_path is not None: coco_config=COCO(os.path.join(args.data_path,"annotations/instances_annotations.json")) cfg.data.train.dataset.img_prefix = os.path.join(args.data_path,"images") cfg.data.train.dataset.ann_file = os.path.join(args.data_path,"annotations/instances_annotations.json") cfg.data.val.img_prefix = os.path.join(args.data_path,"images") cfg.data.val.ann_file = os.path.join(args.data_path,"annotations/instances_annotations.json") cfg.data.test.img_prefix = os.path.join(args.data_path,"images") cfg.data.test.ann_file = os.path.join(args.data_path,"annotations/instances_annotations.json") cfg.classes = () for cat in coco_config.cats.values(): cfg.classes = cfg.classes + tuple([cat['name']]) cfg.data.train.dataset.classes = cfg.classes cfg.data.val.classes = cfg.classes cfg.data.test.classes = cfg.classes #some model will RepeatDataset to speed up training, make sure all dataset path replace to data_path #cfg = Config.fromstring(cfg.dump().replace("ann_file='data/coco/annotations/instances_train2017.json',","ann_file='{}',".format(os.path.join(args.data_path,"annotations/instances_annotations.json"))), ".py") #cfg = Config.fromstring(cfg.dump().replace("img_prefix='data/coco/train2017/',","img_prefix='{}',".format(os.path.join(args.data_path,"images"))), ".py") # replace the classes num fit userdefine dataset #cfg = Config.fromstring(cfg.dump().replace("num_classes=80","num_classes={0}".format(len(coco_config.getCatIds()))), ".py") cfg.model.bbox_head.num_classes = len(coco_config.getCatIds()) print(cfg.dump()) # 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]) if args.resume_from is not None: cfg.resume_from = args.resume_from if args.gpu_ids is not None: cfg.gpu_ids = args.gpu_ids else: cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus) # init distributed env first, since logger depends on the dist info. if args.launcher == 'none': distributed = False else: distributed = True init_dist(args.launcher, **cfg.dist_params) # re-set gpu_ids with distributed training mode _, world_size = get_dist_info() cfg.gpu_ids = range(world_size) # create work_dir mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir)) # dump config cfg.dump(osp.join(cfg.work_dir, 'config.py')) # init the logger before other steps timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime()) log_file = osp.join(cfg.work_dir, f'{timestamp}.log') logger = get_root_logger(log_file=log_file, log_level=cfg.log_level) # init the meta dict to record some important information such as # environment info and seed, which will be logged meta = dict() # log env info env_info_dict = collect_env() env_info = '\n'.join([(f'{k}: {v}') for k, v in env_info_dict.items()]) dash_line = '-' * 60 + '\n' logger.info('Environment info:\n' + dash_line + env_info + '\n' + dash_line) meta['env_info'] = env_info meta['config'] = cfg.pretty_text # log some basic info logger.info(f'Distributed training: {distributed}') logger.info(f'Config:\n{cfg.pretty_text}') # set random seeds #seed = init_random_seed(args.seed) seed = 965702173 logger.info(f'Set random seed to {seed}, ' f'deterministic: {args.deterministic}') set_random_seed(seed, deterministic=args.deterministic) #set_random_seed(seed, deterministic=True) cfg.seed = seed meta['seed'] = seed meta['exp_name'] = osp.basename(args.config) model = build_detector( cfg.model, train_cfg=cfg.get('train_cfg'), test_cfg=cfg.get('test_cfg')) model.init_weights() datasets = [build_dataset(cfg.data.train)] if len(cfg.workflow) == 2: val_dataset = copy.deepcopy(cfg.data.val) val_dataset.pipeline = cfg.data.train.pipeline datasets.append(build_dataset(val_dataset)) if cfg.checkpoint_config is not None: # save mmdet version, config file content and class names in # checkpoints as meta data cfg.checkpoint_config.meta = dict( mmdet_version=__version__ + get_git_hash()[:7], CLASSES=datasets[0].CLASSES) # add an attribute for visualization convenience model.CLASSES = datasets[0].CLASSES train_detector( model, datasets, cfg, distributed=distributed, validate=(not args.no_validate), timestamp=timestamp, meta=meta) #启智平台 shutil.copytree(osp.abspath(osp.join(osp.dirname(__file__),'../../transformer/')), osp.join(args.work_dir, "transformer")) shutil.copy(osp.join(args.train_work_dir, "config.py"), osp.join(args.work_dir, "config.py")) class_name_file = open(osp.join(args.work_dir, "class_names.txt"), 'w') for name in cfg.classes: class_name_file.write(name+'\n') shutil.copy(osp.abspath(osp.join(osp.dirname(__file__),'serve_desc.yaml')), osp.join(args.work_dir, "serve_desc.yaml")) if __name__ == '__main__': main()