def parse_options(is_train=True): parser = argparse.ArgumentParser() parser.add_argument('-opt', type=str, required=True, help='Path to option YAML file.') parser.add_argument('--launcher', choices=['none', 'pytorch', 'slurm'], default='none', help='job launcher') parser.add_argument('--local_rank', type=int, default=0) args = parser.parse_args() opt = parse(args.opt, is_train=is_train) # distributed settings if args.launcher == 'none': opt['dist'] = False print('Disable distributed.', flush=True) else: opt['dist'] = True if args.launcher == 'slurm' and 'dist_params' in opt: init_dist(args.launcher, **opt['dist_params']) else: init_dist(args.launcher) opt['rank'], opt['world_size'] = get_dist_info() # random seed seed = opt.get('manual_seed') if seed is None: seed = random.randint(1, 10000) opt['manual_seed'] = seed set_random_seed(seed + opt['rank']) return opt
def main(): # options parser = argparse.ArgumentParser() parser.add_argument('-opt', type=str, required=True, help='Path to option YAML file.') parser.add_argument('--launcher', choices=['none', 'pytorch', 'slurm'], default='none', help='job launcher') parser.add_argument('--local_rank', type=int, default=0) args = parser.parse_args() opt = parse(args.opt, is_train=True) # distributed training settings if args.launcher == 'none': # non-distributed training opt['dist'] = False print('Disable distributed training.', flush=True) else: opt['dist'] = True if args.launcher == 'slurm' and 'dist_params' in opt: init_dist(args.launcher, **opt['dist_params']) else: init_dist(args.launcher) rank, world_size = get_dist_info() opt['rank'] = rank opt['world_size'] = world_size # load resume states if exists if opt['path'].get('resume_state'): device_id = torch.cuda.current_device() resume_state = torch.load( opt['path']['resume_state'], map_location=lambda storage, loc: storage.cuda(device_id)) else: resume_state = None # mkdir and loggers if resume_state is None: make_exp_dirs(opt) log_file = osp.join(opt['path']['log'], f"train_{opt['name']}_{get_time_str()}.log") logger = get_root_logger(logger_name='basicsr', log_level=logging.INFO, log_file=log_file) logger.info(get_env_info()) logger.info(dict2str(opt)) # initialize tensorboard logger and wandb logger tb_logger = None if opt['logger'].get('use_tb_logger') and 'debug' not in opt['name']: log_dir = './tb_logger/' + opt['name'] if resume_state is None and opt['rank'] == 0: mkdir_and_rename(log_dir) tb_logger = init_tb_logger(log_dir=log_dir) if (opt['logger'].get('wandb') is not None) and (opt['logger']['wandb'].get('project') is not None) and ('debug' not in opt['name']): assert opt['logger'].get('use_tb_logger') is True, ( 'should turn on tensorboard when using wandb') init_wandb_logger(opt) # random seed seed = opt['manual_seed'] if seed is None: seed = random.randint(1, 10000) opt['manual_seed'] = seed logger.info(f'Random seed: {seed}') set_random_seed(seed + rank) torch.backends.cudnn.benchmark = True # torch.backends.cudnn.deterministic = True # create train and val dataloaders train_loader, val_loader = None, None for phase, dataset_opt in opt['datasets'].items(): if phase == 'train': dataset_enlarge_ratio = dataset_opt.get('dataset_enlarge_ratio', 1) train_set = create_dataset(dataset_opt) train_sampler = EnlargedSampler(train_set, world_size, rank, dataset_enlarge_ratio) train_loader = create_dataloader(train_set, dataset_opt, num_gpu=opt['num_gpu'], dist=opt['dist'], sampler=train_sampler, seed=seed) num_iter_per_epoch = math.ceil( len(train_set) * dataset_enlarge_ratio / (dataset_opt['batch_size_per_gpu'] * opt['world_size'])) total_iters = int(opt['train']['total_iter']) total_epochs = math.ceil(total_iters / (num_iter_per_epoch)) logger.info( 'Training statistics:' f'\n\tNumber of train images: {len(train_set)}' f'\n\tDataset enlarge ratio: {dataset_enlarge_ratio}' f'\n\tBatch size per gpu: {dataset_opt["batch_size_per_gpu"]}' f'\n\tWorld size (gpu number): {opt["world_size"]}' f'\n\tRequire iter number per epoch: {num_iter_per_epoch}' f'\n\tTotal epochs: {total_epochs}; iters: {total_iters}.') elif phase == 'val': val_set = create_dataset(dataset_opt) val_loader = create_dataloader(val_set, dataset_opt, num_gpu=opt['num_gpu'], dist=opt['dist'], sampler=None, seed=seed) logger.info( f'Number of val images/folders in {dataset_opt["name"]}: ' f'{len(val_set)}') else: raise ValueError(f'Dataset phase {phase} is not recognized.') assert train_loader is not None # create model if resume_state: check_resume(opt, resume_state['iter']) # modify pretrain_model paths model = create_model(opt) # resume training if resume_state: logger.info(f"Resuming training from epoch: {resume_state['epoch']}, " f"iter: {resume_state['iter']}.") start_epoch = resume_state['epoch'] current_iter = resume_state['iter'] model.resume_training(resume_state) # handle optimizers and schedulers else: start_epoch = 0 current_iter = 0 # create message logger (formatted outputs) msg_logger = MessageLogger(opt, current_iter, tb_logger) # dataloader prefetcher prefetch_mode = opt['datasets']['train'].get('prefetch_mode') if prefetch_mode is None or prefetch_mode == 'cpu': prefetcher = CPUPrefetcher(train_loader) elif prefetch_mode == 'cuda': prefetcher = CUDAPrefetcher(train_loader, opt) logger.info(f'Use {prefetch_mode} prefetch dataloader') if opt['datasets']['train'].get('pin_memory') is not True: raise ValueError('Please set pin_memory=True for CUDAPrefetcher.') else: raise ValueError(f'Wrong prefetch_mode {prefetch_mode}.' "Supported ones are: None, 'cuda', 'cpu'.") # training logger.info( f'Start training from epoch: {start_epoch}, iter: {current_iter}') data_time, iter_time = time.time(), time.time() start_time = time.time() for epoch in range(start_epoch, total_epochs + 1): train_sampler.set_epoch(epoch) prefetcher.reset() train_data = prefetcher.next() while train_data is not None: data_time = time.time() - data_time current_iter += 1 if current_iter > total_iters: break # update learning rate model.update_learning_rate(current_iter, warmup_iter=opt['train'].get( 'warmup_iter', -1)) # training model.feed_data(train_data) model.optimize_parameters(current_iter) iter_time = time.time() - iter_time # log if current_iter % opt['logger']['print_freq'] == 0: log_vars = {'epoch': epoch, 'iter': current_iter} log_vars.update({'lrs': model.get_current_learning_rate()}) log_vars.update({'time': iter_time, 'data_time': data_time}) log_vars.update(model.get_current_log()) msg_logger(log_vars) # save models and training states if current_iter % opt['logger']['save_checkpoint_freq'] == 0: logger.info('Saving models and training states.') model.save(epoch, current_iter) # validation if opt.get('val') is not None and (current_iter % opt['val']['val_freq'] == 0): model.validation(val_loader, current_iter, tb_logger, opt['val']['save_img']) data_time = time.time() iter_time = time.time() train_data = prefetcher.next() # end of iter # end of epoch consumed_time = str( datetime.timedelta(seconds=int(time.time() - start_time))) logger.info(f'End of training. Time consumed: {consumed_time}') logger.info('Save the latest model.') model.save(epoch=-1, current_iter=-1) # -1 stands for the latest if opt.get('val') is not None: model.validation(val_loader, current_iter, tb_logger, opt['val']['save_img']) if tb_logger: tb_logger.close()
def parse_options(root_path, is_train=True): parser = argparse.ArgumentParser() parser.add_argument('-opt', type=str, required=True, help='Path to option YAML file.') parser.add_argument('--launcher', choices=['none', 'pytorch', 'slurm'], default='none', help='job launcher') parser.add_argument('--auto_resume', action='store_true') parser.add_argument('--debug', action='store_true') parser.add_argument('--local_rank', type=int, default=0) parser.add_argument( '--force_yml', nargs='+', default=None, help='Force to update yml files. Examples: train:ema_decay=0.999') args = parser.parse_args() # parse yml to dict with open(args.opt, mode='r') as f: opt = yaml.load(f, Loader=ordered_yaml()[0]) # distributed settings if args.launcher == 'none': opt['dist'] = False print('Disable distributed.', flush=True) else: opt['dist'] = True if args.launcher == 'slurm' and 'dist_params' in opt: init_dist(args.launcher, **opt['dist_params']) else: init_dist(args.launcher) opt['rank'], opt['world_size'] = get_dist_info() # random seed seed = opt.get('manual_seed') if seed is None: seed = random.randint(1, 10000) opt['manual_seed'] = seed set_random_seed(seed + opt['rank']) # force to update yml options if args.force_yml is not None: for entry in args.force_yml: # now do not support creating new keys keys, value = entry.split('=') keys, value = keys.strip(), value.strip() value = _postprocess_yml_value(value) eval_str = 'opt' for key in keys.split(':'): eval_str += f'["{key}"]' eval_str += '=value' # using exec function exec(eval_str) opt['auto_resume'] = args.auto_resume opt['is_train'] = is_train # debug setting if args.debug and not opt['name'].startswith('debug'): opt['name'] = 'debug_' + opt['name'] if opt['num_gpu'] == 'auto': opt['num_gpu'] = torch.cuda.device_count() # datasets for phase, dataset in opt['datasets'].items(): # for multiple datasets, e.g., val_1, val_2; test_1, test_2 phase = phase.split('_')[0] dataset['phase'] = phase if 'scale' in opt: dataset['scale'] = opt['scale'] if dataset.get('dataroot_gt') is not None: dataset['dataroot_gt'] = osp.expanduser(dataset['dataroot_gt']) if dataset.get('dataroot_lq') is not None: dataset['dataroot_lq'] = osp.expanduser(dataset['dataroot_lq']) # paths for key, val in opt['path'].items(): if (val is not None) and ('resume_state' in key or 'pretrain_network' in key): opt['path'][key] = osp.expanduser(val) if is_train: experiments_root = osp.join(root_path, 'experiments', opt['name']) opt['path']['experiments_root'] = experiments_root opt['path']['models'] = osp.join(experiments_root, 'models') opt['path']['training_states'] = osp.join(experiments_root, 'training_states') opt['path']['log'] = experiments_root opt['path']['visualization'] = osp.join(experiments_root, 'visualization') # change some options for debug mode if 'debug' in opt['name']: if 'val' in opt: opt['val']['val_freq'] = 8 opt['logger']['print_freq'] = 1 opt['logger']['save_checkpoint_freq'] = 8 else: # test results_root = osp.join(root_path, 'results', opt['name']) opt['path']['results_root'] = results_root opt['path']['log'] = results_root opt['path']['visualization'] = osp.join(results_root, 'visualization') return opt, args
def main(): # options parser = argparse.ArgumentParser() parser.add_argument('-opt', type=str, help='Path to option YAML file.') parser.add_argument('--launcher', choices=['none', 'pytorch', 'slurm'], default='none', help='job launcher') parser.add_argument('--local_rank', type=int, default=0) args = parser.parse_args() opt = parse(args.opt, is_train=True) # distributed training settings if args.launcher == 'none': # disabled distributed training opt['dist'] = False rank = -1 print('Disabled distributed training.', flush=True) else: opt['dist'] = True if args.launcher == 'slurm' and 'dist_params' in opt: init_dist(args.launcher, **opt['dist_params']) else: init_dist(args.launcher) world_size = torch.distributed.get_world_size() rank = torch.distributed.get_rank() # load resume states if exists if opt['path'].get('resume_state', None): device_id = torch.cuda.current_device() resume_state = torch.load( opt['path']['resume_state'], map_location=lambda storage, loc: storage.cuda(device_id)) else: resume_state = None # mkdir and loggers if resume_state is None: make_exp_dirs(opt) log_file = osp.join(opt['path']['log'], f"train_{opt['name']}_{get_time_str()}.log") logger = get_root_logger(logger_name='basicsr', log_level=logging.INFO, log_file=log_file) logger.info(get_env_info()) logger.info(dict2str(opt)) # initialize tensorboard logger and wandb logger tb_logger = None if opt['logger'].get('use_tb_logger') and 'debug' not in opt['name']: tb_logger = init_tb_logger(log_dir='./tb_logger/' + opt['name']) if (opt['logger'].get('wandb') is not None) and (opt['logger']['wandb'].get('project') is not None) and ('debug' not in opt['name']): assert opt['logger'].get('use_tb_logger') is True, ( 'should turn on tensorboard when using wandb') init_wandb_logger(opt) # random seed seed = opt['train']['manual_seed'] if seed is None: seed = random.randint(1, 10000) logger.info(f'Random seed: {seed}') set_random_seed(seed) torch.backends.cudnn.benchmark = True # torch.backends.cudnn.deterministic = True # create train and val dataloaders train_loader, val_loader = None, None for phase, dataset_opt in opt['datasets'].items(): if phase == 'train': # dataset_ratio: enlarge the size of datasets for each epoch dataset_enlarge_ratio = dataset_opt.get('dataset_enlarge_ratio', 1) train_set = create_dataset(dataset_opt) train_size = int( math.ceil(len(train_set) / dataset_opt['batch_size'])) total_iters = int(opt['train']['niter']) total_epochs = int(math.ceil(total_iters / train_size)) if opt['dist']: train_sampler = DistIterSampler(train_set, world_size, rank, dataset_enlarge_ratio) total_epochs = total_iters / (train_size * dataset_enlarge_ratio) total_epochs = int(math.ceil(total_epochs)) else: train_sampler = None train_loader = create_dataloader(train_set, dataset_opt, opt, train_sampler) logger.info(f'Number of train images: {len(train_set)}, ' f'iters: {train_size}') logger.info( f'Total epochs needed: {total_epochs} for iters {total_iters}') elif phase == 'val': val_set = create_dataset(dataset_opt) val_loader = create_dataloader(val_set, dataset_opt, opt, None) logger.info( f"Number of val images/folders in {dataset_opt['name']}: " f'{len(val_set)}') else: raise NotImplementedError(f'Phase {phase} is not recognized.') assert train_loader is not None # create model if resume_state: check_resume(opt, resume_state['iter']) # modify pretrain_model paths model = create_model(opt) # resume training if resume_state: logger.info(f"Resuming training from epoch: {resume_state['epoch']}, " f"iter: {resume_state['iter']}.") start_epoch = resume_state['epoch'] current_iter = resume_state['iter'] model.resume_training(resume_state) # handle optimizers and schedulers else: current_iter = 0 start_epoch = 0 # create message logger (formatted outputs) msg_logger = MessageLogger(opt, current_iter, tb_logger) # training logger.info( f'Start training from epoch: {start_epoch}, iter: {current_iter}') data_time, iter_time = 0, 0 for epoch in range(start_epoch, total_epochs + 1): if opt['dist']: train_sampler.set_epoch(epoch) for _, train_data in enumerate(train_loader): data_time = time.time() - data_time current_iter += 1 if current_iter > total_iters: break # update learning rate model.update_learning_rate(current_iter, warmup_iter=opt['train']['warmup_iter']) # training model.feed_data(train_data) model.optimize_parameters(current_iter) iter_time = time.time() - iter_time # log if current_iter % opt['logger']['print_freq'] == 0: log_vars = {'epoch': epoch, 'iter': current_iter} log_vars.update({'lrs': model.get_current_learning_rate()}) log_vars.update({'time': iter_time, 'data_time': data_time}) log_vars.update(model.get_current_log()) msg_logger(log_vars) # save models and training states if current_iter % opt['logger']['save_checkpoint_freq'] == 0: logger.info('Saving models and training states.') model.save(epoch, current_iter) # validation if opt['val']['val_freq'] is not None and current_iter % opt[ 'val']['val_freq'] == 0: model.validation(val_loader, current_iter, tb_logger, opt['val']['save_img']) data_time = time.time() iter_time = time.time() # end of iter # end of epoch logger.info('End of training.') logger.info('Saving the latest model.') model.save(epoch=-1, current_iter=-1) # -1 for the latest # last validation if opt['val']['val_freq'] is not None: model.validation(val_loader, current_iter, tb_logger, opt['val']['save_img']) if tb_logger: tb_logger.close()
def main(): # options parser = argparse.ArgumentParser() parser.add_argument('-opt', type=str, required=True, help='Path to option YAML file.') parser.add_argument('--launcher', choices=['none', 'pytorch', 'slurm'], default='none', help='job launcher') parser.add_argument('--local_rank', type=int, default=0) args = parser.parse_args() opt = parse(args.opt, is_train=False) # distributed testing settings if args.launcher == 'none': # non-distributed testing opt['dist'] = False print('Disable distributed testing.', flush=True) else: opt['dist'] = True if args.launcher == 'slurm' and 'dist_params' in opt: init_dist(args.launcher, **opt['dist_params']) else: init_dist(args.launcher) rank, world_size = get_dist_info() opt['rank'] = rank opt['world_size'] = world_size make_exp_dirs(opt) log_file = osp.join(opt['path']['log'], f"test_{opt['name']}_{get_time_str()}.log") logger = get_root_logger(logger_name='basicsr', log_level=logging.INFO, log_file=log_file) logger.info(get_env_info()) logger.info(dict2str(opt)) # random seed seed = opt['manual_seed'] if seed is None: seed = random.randint(1, 10000) opt['manual_seed'] = seed logger.info(f'Random seed: {seed}') set_random_seed(seed + rank) torch.backends.cudnn.benchmark = True # torch.backends.cudnn.deterministic = True # create test dataset and dataloader test_loaders = [] for phase, dataset_opt in sorted(opt['datasets'].items()): test_set = create_dataset(dataset_opt) test_loader = create_dataloader(test_set, dataset_opt, num_gpu=opt['num_gpu'], dist=opt['dist'], sampler=None, seed=seed) logger.info( f"Number of test images in {dataset_opt['name']}: {len(test_set)}") test_loaders.append(test_loader) # create model model = create_model(opt) dummy_input = torch.zeros((1, 3, 800, 800)).to(model.device) dummy_psf = torch.zeros((1, 5, 1, 1)).to(model.device) summary(model.net_g, dummy_input, dummy_psf) for test_loader in test_loaders: test_set_name = test_loader.dataset.opt['name'] mkdir_or_exist(osp.join(opt['path']['visualization'], test_set_name)) logger.info(f'Testing {test_set_name}...') model.validation(test_loader, current_iter=opt['name'], tb_logger=None, save_img=opt['val']['save_img'])
parser.add_argument('--truncation_mean', type=int, default=4096) parser.add_argument( '--ckpt', type=str, default= # noqa: E251 'experiments/pretrained_models/StyleGAN/stylegan2_ffhq_config_f_1024_official-b09c3668.pth' # noqa: E501 ) parser.add_argument('--channel_multiplier', type=int, default=2) parser.add_argument('--randomize_noise', type=bool, default=True) args = parser.parse_args() args.latent = 512 args.n_mlp = 8 os.makedirs('samples', exist_ok=True) set_random_seed(2020) g_ema = StyleGAN2Generator( args.size, args.latent, args.n_mlp, channel_multiplier=args.channel_multiplier).to(device) checkpoint = torch.load(args.ckpt)['params_ema'] g_ema.load_state_dict(checkpoint) if args.truncation < 1: with torch.no_grad(): mean_latent = g_ema.mean_latent(args.truncation_mean) else: mean_latent = None