def test_replace_image_to_tensor(cfg_file): tmp_dir = os.path.abspath(os.path.dirname(os.path.dirname(__file__))) config_file = os.path.join(tmp_dir, cfg_file) cfg = Config.fromfile(config_file) test = cfg.data.test.datasets[0] # cfg.data.test.pipeline is list[dict] # and cfg.data.test.datasets is list[dict] cfg1 = copy.deepcopy(cfg) test1 = copy.deepcopy(test) test1.pipeline = copy.deepcopy(cfg.data.test.pipeline) cfg1.data.test.datasets = [test1] cfg1 = replace_image_to_tensor(cfg1, set_types=['test']) assert cfg1.data.test.pipeline[1]['transforms'][3][ 'type'] == 'DefaultFormatBundle' assert cfg1.data.test.datasets[0].pipeline[1]['transforms'][3][ 'type'] == 'DefaultFormatBundle' # cfg.data.test.pipeline is list[list[dict]] # and cfg.data.test.datasets is list[list[dict]] cfg2 = copy.deepcopy(cfg) test2 = copy.deepcopy(test) test2.pipeline = copy.deepcopy(cfg.data.test.pipeline) cfg2.data.test.datasets = [[test2], [test2]] cfg2.data.test.pipeline = [ cfg2.data.test.pipeline, cfg2.data.test.pipeline ] cfg2 = replace_image_to_tensor(cfg2, set_types=['test']) assert cfg2.data.test.pipeline[0][1]['transforms'][3][ 'type'] == 'DefaultFormatBundle' assert cfg2.data.test.datasets[0][0].pipeline[1]['transforms'][3][ 'type'] == 'DefaultFormatBundle'
def main(): args = parse_args() assert ( args.out or args.eval or args.format_only or args.show or args.show_dir), ( 'Please specify at least one operation (save/eval/format/show the ' 'results / save the results) with the argument "--out", "--eval"' ', "--format-only", "--show" or "--show-dir".') if args.eval and args.format_only: raise ValueError('--eval and --format_only cannot be both specified.') if args.out is not None and not args.out.endswith(('.pkl', '.pickle')): raise ValueError('The output file must be a pkl file.') cfg = Config.fromfile(args.config) if args.cfg_options is not None: cfg.merge_from_dict(args.cfg_options) setup_multi_processes(cfg) # set cudnn_benchmark if cfg.get('cudnn_benchmark', False): torch.backends.cudnn.benchmark = True if cfg.model.get('pretrained'): cfg.model.pretrained = None if cfg.model.get('neck'): if isinstance(cfg.model.neck, list): for neck_cfg in cfg.model.neck: if neck_cfg.get('rfp_backbone'): if neck_cfg.rfp_backbone.get('pretrained'): neck_cfg.rfp_backbone.pretrained = None elif cfg.model.neck.get('rfp_backbone'): if cfg.model.neck.rfp_backbone.get('pretrained'): cfg.model.neck.rfp_backbone.pretrained = None # in case the test dataset is concatenated samples_per_gpu = (cfg.data.get('test_dataloader', {})).get( 'samples_per_gpu', cfg.data.get('samples_per_gpu', 1)) if samples_per_gpu > 1: cfg = disable_text_recog_aug_test(cfg) cfg = replace_image_to_tensor(cfg) # init distributed env first, since logger depends on the dist info. if args.launcher == 'none': cfg.gpu_ids = [args.gpu_id] distributed = False else: distributed = True init_dist(args.launcher, **cfg.dist_params) # build the dataloader dataset = build_dataset(cfg.data.test, dict(test_mode=True)) # step 1: give default values and override (if exist) from cfg.data default_loader_cfg = { **dict(seed=cfg.get('seed'), drop_last=False, dist=distributed), **({} if torch.__version__ != 'parrots' else dict( prefetch_num=2, pin_memory=False, )) } default_loader_cfg.update({ k: v for k, v in cfg.data.items() if k not in [ 'train', 'val', 'test', 'train_dataloader', 'val_dataloader', 'test_dataloader' ] }) test_loader_cfg = { **default_loader_cfg, **dict(shuffle=False, drop_last=False), **cfg.data.get('test_dataloader', {}), **dict(samples_per_gpu=samples_per_gpu) } data_loader = build_dataloader(dataset, **test_loader_cfg) # build the model and load checkpoint cfg.model.train_cfg = None model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg')) model = revert_sync_batchnorm(model) fp16_cfg = cfg.get('fp16', None) if fp16_cfg is not None: wrap_fp16_model(model) load_checkpoint(model, args.checkpoint, map_location='cpu') if args.fuse_conv_bn: model = fuse_conv_bn(model) if not distributed: model = MMDataParallel(model, device_ids=cfg.gpu_ids) is_kie = cfg.model.type in ['SDMGR'] outputs = single_gpu_test(model, data_loader, args.show, args.show_dir, is_kie, args.show_score_thr) else: model = MMDistributedDataParallel( model.cuda(), device_ids=[torch.cuda.current_device()], broadcast_buffers=False) outputs = multi_gpu_test(model, data_loader, args.tmpdir, args.gpu_collect) rank, _ = get_dist_info() if rank == 0: if args.out: print(f'\nwriting results to {args.out}') mmcv.dump(outputs, args.out) kwargs = {} if args.eval_options is None else args.eval_options if args.format_only: dataset.format_results(outputs, **kwargs) if args.eval: eval_kwargs = cfg.get('evaluation', {}).copy() # hard-code way to remove EvalHook args for key in [ 'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best', 'rule' ]: eval_kwargs.pop(key, None) eval_kwargs.update(dict(metric=args.eval, **kwargs)) print(dataset.evaluate(outputs, **eval_kwargs))
def train_detector(model, dataset, cfg, distributed=False, validate=False, timestamp=None, meta=None): logger = get_root_logger(cfg.log_level) # prepare data loaders dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset] # step 1: give default values and override (if exist) from cfg.data loader_cfg = { **dict(seed=cfg.get('seed'), drop_last=False, dist=distributed, num_gpus=len(cfg.gpu_ids)), **({} if torch.__version__ != 'parrots' else dict( prefetch_num=2, pin_memory=False, )), **dict((k, cfg.data[k]) for k in [ 'samples_per_gpu', 'workers_per_gpu', 'shuffle', 'seed', 'drop_last', 'prefetch_num', 'pin_memory', 'persistent_workers', ] if k in cfg.data) } # step 2: cfg.data.train_dataloader has highest priority train_loader_cfg = dict(loader_cfg, **cfg.data.get('train_dataloader', {})) data_loaders = [build_dataloader(ds, **train_loader_cfg) for ds in dataset] # put model on gpus if distributed: find_unused_parameters = cfg.get('find_unused_parameters', False) # Sets the `find_unused_parameters` parameter in # torch.nn.parallel.DistributedDataParallel model = MMDistributedDataParallel( model.cuda(), device_ids=[torch.cuda.current_device()], broadcast_buffers=False, find_unused_parameters=find_unused_parameters) else: if not torch.cuda.is_available(): assert digit_version(mmcv.__version__) >= digit_version('1.4.4'), \ 'Please use MMCV >= 1.4.4 for CPU training!' model = MMDataParallel(model, device_ids=cfg.gpu_ids) # build runner optimizer = build_optimizer(model, cfg.optimizer) if 'runner' not in cfg: cfg.runner = { 'type': 'EpochBasedRunner', 'max_epochs': cfg.total_epochs } warnings.warn( 'config is now expected to have a `runner` section, ' 'please set `runner` in your config.', UserWarning) else: if 'total_epochs' in cfg: assert cfg.total_epochs == cfg.runner.max_epochs runner = build_runner(cfg.runner, default_args=dict(model=model, optimizer=optimizer, work_dir=cfg.work_dir, logger=logger, meta=meta)) # an ugly workaround to make .log and .log.json filenames the same runner.timestamp = timestamp # fp16 setting fp16_cfg = cfg.get('fp16', None) if fp16_cfg is not None: optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config, **fp16_cfg, distributed=distributed) elif distributed and 'type' not in cfg.optimizer_config: optimizer_config = OptimizerHook(**cfg.optimizer_config) else: optimizer_config = cfg.optimizer_config # register hooks runner.register_training_hooks(cfg.lr_config, optimizer_config, cfg.checkpoint_config, cfg.log_config, cfg.get('momentum_config', None), custom_hooks_config=cfg.get( 'custom_hooks', None)) if distributed: if isinstance(runner, EpochBasedRunner): runner.register_hook(DistSamplerSeedHook()) # register eval hooks if validate: val_samples_per_gpu = (cfg.data.get('val_dataloader', {})).get( 'samples_per_gpu', cfg.data.get('samples_per_gpu', 1)) if val_samples_per_gpu > 1: # Support batch_size > 1 in test for text recognition # by disable MultiRotateAugOCR since it is useless for most case cfg = disable_text_recog_aug_test(cfg) cfg = replace_image_to_tensor(cfg) val_dataset = build_dataset(cfg.data.val, dict(test_mode=True)) val_loader_cfg = { **loader_cfg, **dict(shuffle=False, drop_last=False), **cfg.data.get('val_dataloader', {}), **dict(samples_per_gpu=val_samples_per_gpu) } val_dataloader = build_dataloader(val_dataset, **val_loader_cfg) eval_cfg = cfg.get('evaluation', {}) eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner' eval_hook = DistEvalHook if distributed else EvalHook runner.register_hook(eval_hook(val_dataloader, **eval_cfg)) if cfg.resume_from: runner.resume(cfg.resume_from) elif cfg.load_from: runner.load_checkpoint(cfg.load_from) runner.run(data_loaders, cfg.workflow)