def main(): # 1. Get input arguments args = get_args() # 2. Create config instance from args above cfg = get_default_config() cfg.use_gpu = torch.cuda.is_available() if args.config_file: cfg.merge_from_file(args.config_file) reset_config(cfg, args) cfg.merge_from_list(args.opts) set_random_seed(cfg.train.seed) log_name = 'test.log' if cfg.test.evaluate else 'train.log' log_name += time.strftime('-%Y-%m-%d-%H-%M-%S') sys.stdout = Logger(osp.join(cfg.data.save_dir, log_name)) print('Show configuration\n{}\n'.format(cfg)) print('Collecting env info ...') print('** System info **\n{}\n'.format(collect_env_info())) if cfg.use_gpu: torch.backends.cudnn.benchmark = True # 3. Create DataManager Instance datamanager = build_datamanager(cfg) print('Building model: {}'.format(cfg.model.name)) model = torchreid.models.build_model( name=cfg.model.name, num_classes=datamanager.num_train_pids, loss=cfg.loss.name, pretrained=cfg.model.pretrained, use_gpu=cfg.use_gpu) num_params, flops = compute_model_complexity( model, (1, 3, cfg.data.height, cfg.data.width)) print('Model complexity: params={:,} flops={:,}'.format(num_params, flops)) if cfg.model.load_weights and check_isfile(cfg.model.load_weights): load_pretrained_weights(model, cfg.model.load_weights) if cfg.use_gpu: model = nn.DataParallel(model).cuda() optimizer = torchreid.optim.build_optimizer(model, **optimizer_kwargs(cfg)) scheduler = torchreid.optim.build_lr_scheduler(optimizer, **lr_scheduler_kwargs(cfg)) if cfg.model.resume and check_isfile(cfg.model.resume): cfg.train.start_epoch = resume_from_checkpoint(cfg.model.resume, model, optimizer=optimizer, scheduler=scheduler) print('Building {}-engine for {}-reid'.format(cfg.loss.name, cfg.data.type)) # Build engine and run engine = build_engine(cfg, datamanager, model, optimizer, scheduler) engine.run(**engine_run_kwargs(cfg))
def build_auxiliary_model(config_file, num_classes, use_gpu, device_ids, num_iter, lr=None, nncf_aux_config_changes=None, aux_config_opts=None, aux_pretrained_dict=None): aux_cfg = get_default_config() aux_cfg.use_gpu = use_gpu merge_from_files_with_base(aux_cfg, config_file) if nncf_aux_config_changes: print( f'applying to aux config changes from NNCF aux config {nncf_aux_config_changes}' ) if not isinstance(nncf_aux_config_changes, CfgNode): nncf_aux_config_changes = CfgNode(nncf_aux_config_changes) aux_cfg.merge_from_other_cfg(nncf_aux_config_changes) if aux_config_opts: print(f'applying to aux config changes from command line arguments, ' f'the changes are:\n{pformat(aux_config_opts)}') aux_cfg.merge_from_list(aux_config_opts) print(f'\nShow auxiliary configuration\n{aux_cfg}\n') if lr is not None: aux_cfg.train.lr = lr print(f"setting learning rate from main model: {lr}") model = torchreid.models.build_model(**model_kwargs(aux_cfg, num_classes)) optimizer = torchreid.optim.build_optimizer(model, **optimizer_kwargs(aux_cfg)) scheduler = torchreid.optim.build_lr_scheduler( optimizer=optimizer, num_iter=num_iter, **lr_scheduler_kwargs(aux_cfg)) if aux_cfg.model.resume and check_isfile(aux_cfg.model.resume): aux_cfg.train.start_epoch = resume_from_checkpoint( aux_cfg.model.resume, model, optimizer=optimizer, scheduler=scheduler) elif aux_pretrained_dict is not None: load_pretrained_weights(model, pretrained_dict=aux_pretrained_dict) elif aux_cfg.model.load_weights and check_isfile( aux_cfg.model.load_weights): load_pretrained_weights(model, aux_cfg.model.load_weights) if aux_cfg.use_gpu: assert device_ids is not None if len(device_ids) > 1: model = DataParallel(model, device_ids=device_ids, output_device=0).cuda(device_ids[0]) else: model = model.cuda(device_ids[0]) return model, optimizer, scheduler
def main(): global args set_random_seed(args.seed) if not args.use_avai_gpus: os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices use_gpu = torch.cuda.is_available() and not args.use_cpu log_name = 'test.log' if args.evaluate else 'train.log' log_name += time.strftime('-%Y-%m-%d-%H-%M-%S') sys.stdout = Logger(osp.join(args.save_dir, log_name)) print('** Arguments **') arg_keys = list(args.__dict__.keys()) arg_keys.sort() for key in arg_keys: print('{}: {}'.format(key, args.__dict__[key])) print('\n') print('Collecting env info ...') print('** System info **\n{}\n'.format(collect_env_info())) if use_gpu: torch.backends.cudnn.benchmark = True else: warnings.warn( 'Currently using CPU, however, GPU is highly recommended') datamanager = build_datamanager(args) print('Building model: {}'.format(args.arch)) model = torchreid.models.build_model( name=args.arch, num_classes=datamanager.num_train_pids, loss=args.loss.lower(), pretrained=(not args.no_pretrained), use_gpu=use_gpu) num_params, flops = compute_model_complexity( model, (1, 3, args.height, args.width)) print('Model complexity: params={:,} flops={:,}'.format(num_params, flops)) if args.load_weights and check_isfile(args.load_weights): load_pretrained_weights(model, args.load_weights) if use_gpu: model = nn.DataParallel(model).cuda() optimizer = torchreid.optim.build_optimizer(model, **optimizer_kwargs(args)) scheduler = torchreid.optim.build_lr_scheduler(optimizer, **lr_scheduler_kwargs(args)) if args.resume and check_isfile(args.resume): args.start_epoch = resume_from_checkpoint(args.resume, model, optimizer=optimizer) print('Building {}-engine for {}-reid'.format(args.loss, args.app)) engine = build_engine(args, datamanager, model, optimizer, scheduler) engine.run(**engine_run_kwargs(args))
def main(): parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter) parser.add_argument('--config-file', type=str, default='', help='path to config file') parser.add_argument('-s', '--sources', type=str, nargs='+', help='source datasets (delimited by space)') parser.add_argument('-t', '--targets', type=str, nargs='+', help='target datasets (delimited by space)') parser.add_argument('--root', type=str, default='', help='path to data root') parser.add_argument('opts', default=None, nargs=argparse.REMAINDER, help='Modify config options using the command-line') args = parser.parse_args() cfg = get_default_config() cfg.use_gpu = torch.cuda.is_available() if args.config_file: cfg.merge_from_file(args.config_file) reset_config(cfg, args) cfg.merge_from_list(args.opts) set_random_seed(cfg.train.seed) log_name = 'test.log' if cfg.test.evaluate else 'train.log' log_name += time.strftime('-%Y-%m-%d-%H-%M-%S') sys.stdout = Logger(osp.join(cfg.data.save_dir, log_name)) print('Show configuration\n{}\n'.format(cfg)) print('Collecting env info ...') print('** System info **\n{}\n'.format(collect_env_info())) if cfg.use_gpu: torch.backends.cudnn.benchmark = True datamanager = build_datamanager(cfg) print('Building model: {}'.format(cfg.model.name)) model = torchreid.models.build_model(**model_kwargs(cfg, datamanager.num_train_pids)) num_params, flops = compute_model_complexity(model, (1, 3, cfg.data.height, cfg.data.width)) print('Model complexity: params={:,} flops={:,}'.format(num_params, flops)) if cfg.model.load_weights and check_isfile(cfg.model.load_weights): if cfg.model.pretrained and not cfg.test.evaluate: state_dict = torch.load(cfg.model.load_weights) model.load_pretrained_weights(state_dict) else: load_pretrained_weights(model, cfg.model.load_weights) if cfg.use_gpu: model = nn.DataParallel(model).cuda() optimizer = torchreid.optim.build_optimizer(model, **optimizer_kwargs(cfg)) scheduler = torchreid.optim.build_lr_scheduler(optimizer, **lr_scheduler_kwargs(cfg)) if cfg.model.resume and check_isfile(cfg.model.resume): cfg.train.start_epoch = resume_from_checkpoint( cfg.model.resume, model, optimizer=optimizer, scheduler=scheduler ) print('Building {}-engine for {}-reid'.format(cfg.loss.name, cfg.data.type)) engine = build_engine(cfg, datamanager, model, optimizer, scheduler) engine.run(**engine_run_kwargs(cfg))
def main(): global args set_random_seed(args.seed) if not args.use_avai_gpus: os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices use_gpu = (torch.cuda.is_available() and not args.use_cpu) log_name = 'test.log' if args.evaluate else 'train.log' sys.stdout = Logger(osp.join(args.save_dir, log_name)) print('==========\nArgs:{}\n=========='.format(args)) if use_gpu: print('Currently using GPU {}'.format(args.gpu_devices)) torch.backends.cudnn.benchmark = True else: warnings.warn( 'Currently using CPU, however, GPU is highly recommended') datamanager = build_datamanager(args) print('Building model: {}'.format(args.arch)) model = torchreid.models.build_model( name=args.arch, num_classes=datamanager.num_train_pids, loss=args.loss.lower(), pretrained=(not args.no_pretrained), use_gpu=use_gpu) num_params, flops = compute_model_complexity( model, (1, 3, args.height, args.width)) print('Model complexity: params={:,} flops={:,}'.format(num_params, flops)) if args.load_weights and check_isfile(args.load_weights): load_pretrained_weights(model, args.load_weights) if use_gpu: model = nn.DataParallel(model).cuda() optimizer = torchreid.optim.build_optimizer(model, **optimizer_kwargs(args)) scheduler = torchreid.optim.build_lr_scheduler(optimizer, **lr_scheduler_kwargs(args)) if args.resume and check_isfile(args.resume): args.start_epoch = resume_from_checkpoint(args.resume, model, optimizer=optimizer) print('Building {}-engine for {}-reid'.format(args.loss, args.app)) engine = build_engine(args, datamanager, model, optimizer, scheduler) engine.run(**engine_run_kwargs(args))
def main(): parser = argparse.ArgumentParser( formatter_class=argparse.ArgumentDefaultsHelpFormatter ) parser.add_argument( '--config-file', type=str, default='', help='path to config file' ) parser.add_argument( '-s', '--sources', type=str, nargs='+', help='source datasets (delimited by space)' ) parser.add_argument( '-t', '--targets', type=str, nargs='+', help='target datasets (delimited by space)' ) parser.add_argument( '--transforms', type=str, nargs='+', help='data augmentation' ) parser.add_argument( '--root', type=str, default='', help='path to data root' ) parser.add_argument( '--gpu-devices', type=str, default='', ) parser.add_argument( 'opts', default=None, nargs=argparse.REMAINDER, help='Modify config options using the command-line' ) args = parser.parse_args() cfg = get_default_config() cfg.use_gpu = torch.cuda.is_available() if args.config_file: cfg.merge_from_file(args.config_file) reset_config(cfg, args) cfg.merge_from_list(args.opts) set_random_seed(cfg.train.seed) if cfg.use_gpu and args.gpu_devices: # if gpu_devices is not specified, all available gpus will be used os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices log_name = 'test.log' if cfg.test.evaluate else 'train.log' log_name += time.strftime('-%Y-%m-%d-%H-%M-%S') sys.stdout = Logger(osp.join(cfg.data.save_dir, log_name)) print('Show configuration\n{}\n'.format(cfg)) print('Collecting env info ...') print('** System info **\n{}\n'.format(collect_env_info())) if cfg.use_gpu: torch.backends.cudnn.benchmark = True datamanager = torchreid.data.ImageDataManager(**imagedata_kwargs(cfg)) print('Building model: {}'.format(cfg.model.name)) model = osnet_models.build_model( cfg.model.name, num_classes=datamanager.num_train_pids ) num_params, flops = compute_model_complexity( model, (1, 3, cfg.data.height, cfg.data.width) ) print('Model complexity: params={:,} flops={:,}'.format(num_params, flops)) if cfg.use_gpu: model = nn.DataParallel(model).cuda() optimizer = torchreid.optim.build_optimizer(model, **optimizer_kwargs(cfg)) scheduler = torchreid.optim.build_lr_scheduler( optimizer, **lr_scheduler_kwargs(cfg) ) if cfg.model.resume and check_isfile(cfg.model.resume): cfg.train.start_epoch = resume_from_checkpoint( cfg.model.resume, model, optimizer=optimizer ) print('Building NAS engine') engine = ImageSoftmaxNASEngine( datamanager, model, optimizer, scheduler=scheduler, use_gpu=cfg.use_gpu, label_smooth=cfg.loss.softmax.label_smooth, mc_iter=cfg.nas.mc_iter, init_lmda=cfg.nas.init_lmda, min_lmda=cfg.nas.min_lmda, lmda_decay_step=cfg.nas.lmda_decay_step, lmda_decay_rate=cfg.nas.lmda_decay_rate, fixed_lmda=cfg.nas.fixed_lmda ) engine.run(**engine_run_kwargs(cfg)) print('*** Display the found architecture ***') if cfg.use_gpu: model.module.build_child_graph() else: model.build_child_graph()
def main(): parser = argparse.ArgumentParser( formatter_class=argparse.ArgumentDefaultsHelpFormatter) parser.add_argument('--config-file', type=str, default='', help='path to config file') parser.add_argument('-s', '--sources', type=str, nargs='+', help='source datasets (delimited by space)') parser.add_argument('-t', '--targets', type=str, nargs='+', help='target datasets (delimited by space)') parser.add_argument('--transforms', type=str, nargs='+', help='data augmentation') parser.add_argument('--root', type=str, default='', help='path to data root') parser.add_argument('opts', default=None, nargs=argparse.REMAINDER, help='Modify config options using the command-line') args = parser.parse_args() cfg = get_default_config() cfg.use_gpu = torch.cuda.is_available() if args.config_file: cfg.merge_from_file(args.config_file) reset_config(cfg, args) cfg.merge_from_list(args.opts) set_random_seed(cfg.train.seed) log_name = 'test.log' if cfg.test.evaluate else 'train.log' log_name += time.strftime('-%Y-%m-%d-%H-%M-%S') sys.stdout = Logger(osp.join(cfg.data.save_dir, log_name)) print('Show configuration\n{}\n'.format(cfg)) print('Collecting env info ...') print('** System info **\n{}\n'.format(collect_env_info())) if cfg.use_gpu: torch.backends.cudnn.benchmark = True datamanager = torchreid.data.ImageDataManager(**imagedata_kwargs(cfg)) print('Building model-1: {}'.format(cfg.model.name)) model1 = torchreid.models.build_model( name=cfg.model.name, num_classes=datamanager.num_train_pids, loss=cfg.loss.name, pretrained=cfg.model.pretrained, use_gpu=cfg.use_gpu) num_params, flops = compute_model_complexity( model1, (1, 3, cfg.data.height, cfg.data.width)) print('Model complexity: params={:,} flops={:,}'.format(num_params, flops)) print('Copying model-1 to model-2') model2 = copy.deepcopy(model1) if cfg.model.load_weights1 and check_isfile(cfg.model.load_weights1): load_pretrained_weights(model1, cfg.model.load_weights1) if cfg.model.load_weights2 and check_isfile(cfg.model.load_weights2): load_pretrained_weights(model2, cfg.model.load_weights2) if cfg.use_gpu: model1 = nn.DataParallel(model1).cuda() model2 = nn.DataParallel(model2).cuda() optimizer1 = torchreid.optim.build_optimizer(model1, **optimizer_kwargs(cfg)) scheduler1 = torchreid.optim.build_lr_scheduler(optimizer1, **lr_scheduler_kwargs(cfg)) optimizer2 = torchreid.optim.build_optimizer(model2, **optimizer_kwargs(cfg)) scheduler2 = torchreid.optim.build_lr_scheduler(optimizer2, **lr_scheduler_kwargs(cfg)) if cfg.model.resume1 and check_isfile(cfg.model.resume1): cfg.train.start_epoch = resume_from_checkpoint(cfg.model.resume1, model1, optimizer=optimizer1, scheduler=scheduler1) if cfg.model.resume2 and check_isfile(cfg.model.resume2): resume_from_checkpoint(cfg.model.resume2, model2, optimizer=optimizer2, scheduler=scheduler2) print('Building DML-engine for image-reid') engine = ImageDMLEngine(datamanager, model1, optimizer1, scheduler1, model2, optimizer2, scheduler2, margin=cfg.loss.triplet.margin, weight_t=cfg.loss.triplet.weight_t, weight_x=cfg.loss.triplet.weight_x, weight_ml=cfg.loss.dml.weight_ml, use_gpu=cfg.use_gpu, label_smooth=cfg.loss.softmax.label_smooth, deploy=cfg.model.deploy) engine.run(**engine_run_kwargs(cfg))
def main(): parser = build_base_argparser() parser.add_argument('-e', '--auxiliary-models-cfg', type=str, nargs='*', default='', help='path to extra config files') parser.add_argument('--split-models', action='store_true', help='whether to split models on own gpu') parser.add_argument('--enable_quantization', action='store_true', help='Enable NNCF quantization algorithm') parser.add_argument('--enable_pruning', action='store_true', help='Enable NNCF pruning algorithm') parser.add_argument( '--aux-config-opts', nargs='+', default=None, help='Modify aux config options using the command-line') args = parser.parse_args() cfg = get_default_config() cfg.use_gpu = torch.cuda.is_available() and args.gpu_num > 0 if args.config_file: merge_from_files_with_base(cfg, args.config_file) reset_config(cfg, args) cfg.merge_from_list(args.opts) is_nncf_used = args.enable_quantization or args.enable_pruning if is_nncf_used: print(f'Using NNCF -- making NNCF changes in config') cfg = make_nncf_changes_in_config(cfg, args.enable_quantization, args.enable_pruning, args.opts) set_random_seed(cfg.train.seed, cfg.train.deterministic) log_name = 'test.log' if cfg.test.evaluate else 'train.log' log_name += time.strftime('-%Y-%m-%d-%H-%M-%S') sys.stdout = Logger(osp.join(cfg.data.save_dir, log_name)) print('Show configuration\n{}\n'.format(cfg)) if cfg.use_gpu: torch.backends.cudnn.benchmark = True num_aux_models = len(cfg.mutual_learning.aux_configs) datamanager = build_datamanager(cfg, args.classes) num_train_classes = datamanager.num_train_pids print('Building main model: {}'.format(cfg.model.name)) model = torchreid.models.build_model( **model_kwargs(cfg, num_train_classes)) macs, num_params = get_model_complexity_info( model, (3, cfg.data.height, cfg.data.width), as_strings=False, verbose=False, print_per_layer_stat=False) print('Main model complexity: params={:,} flops={:,}'.format( num_params, macs * 2)) aux_lr = cfg.train.lr # placeholder, needed for aux models, may be filled by nncf part below if is_nncf_used: print('Begin making NNCF changes in model') if cfg.use_gpu: model.cuda() compression_ctrl, model, cfg, aux_lr, nncf_metainfo = \ make_nncf_changes_in_training(model, cfg, args.classes, args.opts) should_freeze_aux_models = True print(f'should_freeze_aux_models = {should_freeze_aux_models}') print('End making NNCF changes in model') else: compression_ctrl = None should_freeze_aux_models = False nncf_metainfo = None # creating optimizer and scheduler -- it should be done after NNCF part, since # NNCF could change some parameters optimizer = torchreid.optim.build_optimizer(model, **optimizer_kwargs(cfg)) if cfg.lr_finder.enable and not cfg.model.resume: scheduler = None else: scheduler = torchreid.optim.build_lr_scheduler( optimizer=optimizer, num_iter=datamanager.num_iter, **lr_scheduler_kwargs(cfg)) # Loading model (and optimizer and scheduler in case of resuming training). # Note that if NNCF is used, loading is done inside NNCF part, so loading here is not required. if cfg.model.resume and check_isfile( cfg.model.resume) and not is_nncf_used: device_ = 'cuda' if cfg.use_gpu else 'cpu' cfg.train.start_epoch = resume_from_checkpoint(cfg.model.resume, model, optimizer=optimizer, scheduler=scheduler, device=device_) elif cfg.model.load_weights and not is_nncf_used: load_pretrained_weights(model, cfg.model.load_weights) if cfg.model.type == 'classification': check_classification_classes(model, datamanager, args.classes, test_only=cfg.test.evaluate) model, extra_device_ids = put_main_model_on_the_device( model, cfg.use_gpu, args.gpu_num, num_aux_models, args.split_models) if cfg.lr_finder.enable and not cfg.test.evaluate and not cfg.model.resume: aux_lr, model, optimizer, scheduler = run_lr_finder( cfg, datamanager, model, optimizer, scheduler, args.classes, rebuild_model=True, gpu_num=args.gpu_num, split_models=args.split_models) log_dir = cfg.data.tb_log_dir if cfg.data.tb_log_dir else cfg.data.save_dir run_training(cfg, datamanager, model, optimizer, scheduler, extra_device_ids, aux_lr, tb_writer=SummaryWriter(log_dir=log_dir), should_freeze_aux_models=should_freeze_aux_models, nncf_metainfo=nncf_metainfo, compression_ctrl=compression_ctrl)
def main(): # Load model configuration parser = argparse.ArgumentParser() parser.add_argument('-c', '--config', required=True, help='path to configuration file') args = parser.parse_args() with open(args.config, "r") as ymlfile: config = yaml.load(ymlfile, Loader=yaml.FullLoader) # Automatically add sub-folder name to config["save_dir"], with the same name # as the config file. For example, config["save_dir"] is typically "logs", # so this would change config["save_dir"] to "logs/exp01", for example, so that # we don't need to change the save_dir in every single config file (it instead # automatically generates it from the name of the config file). experiment_number = pathlib.Path(args.config).stem config["save_dir"] = os.path.join(config["save_dir"], experiment_number) # Set random seeds set_random_seed(config["seed"]) # Set up GPU if not config["use_avai_gpus"]: os.environ['CUDA_VISIBLE_DEVICES'] = config["gpu_devices"] use_gpu = torch.cuda.is_available() and not config["use_cpu"] # Set up log files log_name = 'test.log' if config["evaluate"] else 'train.log' log_name += time.strftime('-%Y-%m-%d-%H-%M-%S') sys.stdout = Logger(osp.join(config["save_dir"], log_name)) # Prepare for training print('==========\nArgs:{}\n=========='.format(config)) print('Collecting env info ...') print('** System info **\n{}\n'.format(collect_env_info())) if use_gpu: torch.backends.cudnn.benchmark = True else: warnings.warn( 'Currently using CPU, however, GPU is highly recommended') # Build datamanager and model datamanager = build_datamanager(config) print('Building model: {}'.format(config["arch"])) model = torchreid.models.build_model( name=config["arch"], num_classes=datamanager.num_train_pids, loss=config["loss"].lower(), pretrained=(not config["no_pretrained"]), use_gpu=use_gpu) # Compute model complexity num_params, flops = compute_model_complexity( model, (1, 3, config["height"], config["width"])) print('Model complexity: params={:,} flops={:,}'.format(num_params, flops)) # Load pretrained weights if necessary if config["load_weights"] and check_isfile(config["load_weights"]): load_pretrained_weights(model, config["load_weights"]) # Set up multi-gpu if use_gpu: model = nn.DataParallel(model).cuda() # Model settings optimizer = torchreid.optim.build_optimizer(model, **optimizer_kwargs(config)) scheduler = torchreid.optim.build_lr_scheduler( optimizer, **lr_scheduler_kwargs(config)) if config["resume"] and check_isfile(config["resume"]): config["start_epoch"] = resume_from_checkpoint(config["resume"], model, optimizer=optimizer) print('Building {}-engine for {}-reid'.format(config["loss"], config["app"])) engine = build_engine(config, datamanager, model, optimizer, scheduler) engine.run(**engine_run_kwargs(config))