diff --git a/_paramters.py b/_paramters.py index 97865d8..7a5258e 100644 --- a/_paramters.py +++ b/_paramters.py @@ -31,13 +31,25 @@ main_arg_parser.add_argument("--data_mixup", type=strtobool, default=False, help main_arg_parser.add_argument("--data_stretch", type=strtobool, default=True, help="") # Transformation Parameters -main_arg_parser.add_argument("--data_loudness_ratio", type=float, default=0.4, help="") # 0.4 -main_arg_parser.add_argument("--data_shift_ratio", type=float, default=0.3, help="") # 0.3 -main_arg_parser.add_argument("--data_noise_ratio", type=float, default=0.4, help="") # 0.4 -main_arg_parser.add_argument("--data_mask_ratio", type=float, default=0.2, help="") # 0.2 +main_arg_parser.add_argument("--data_loudness_ratio", type=float, default=0, help="") # 0.4 +main_arg_parser.add_argument("--data_shift_ratio", type=float, default=0, help="") # 0.3 +main_arg_parser.add_argument("--data_noise_ratio", type=float, default=0, help="") # 0.4 +main_arg_parser.add_argument("--data_mask_ratio", type=float, default=0, help="") # 0.2 main_arg_parser.add_argument("--data_speed_ratio", type=float, default=0.3, help="") # 0.3 main_arg_parser.add_argument("--data_speed_factor", type=float, default=0.7, help="") # 0.7 +# Model Parameters +main_arg_parser.add_argument("--model_type", type=str, default="RCC", help="") +main_arg_parser.add_argument("--model_secondary_type", type=str, default="RCC", help="") +main_arg_parser.add_argument("--model_weight_init", type=str, default="xavier_normal_", help="") +main_arg_parser.add_argument("--model_activation", type=str, default="leaky_relu", help="") +main_arg_parser.add_argument("--model_filters", type=str, default="[32, 64, 128, 64]", help="") +main_arg_parser.add_argument("--model_classes", type=int, default=2, help="") +main_arg_parser.add_argument("--model_lat_dim", type=int, default=128, help="") +main_arg_parser.add_argument("--model_bias", type=strtobool, default=True, help="") +main_arg_parser.add_argument("--model_norm", type=strtobool, default=True, help="") +main_arg_parser.add_argument("--model_dropout", type=float, default=0.2, help="") + # Training Parameters main_arg_parser.add_argument("--train_outpath", type=str, default="output", help="") main_arg_parser.add_argument("--train_version", type=strtobool, required=False, help="") @@ -49,18 +61,6 @@ main_arg_parser.add_argument("--train_batch_size", type=int, default=300, help=" main_arg_parser.add_argument("--train_lr", type=float, default=1e-4, help="") main_arg_parser.add_argument("--train_num_sanity_val_steps", type=int, default=0, help="") -# Model Parameters -main_arg_parser.add_argument("--model_type", type=str, default="BCMC", help="") -main_arg_parser.add_argument("--model_secondary_type", type=str, default="BCMC", help="") -main_arg_parser.add_argument("--model_weight_init", type=str, default="xavier_normal_", help="") -main_arg_parser.add_argument("--model_activation", type=str, default="leaky_relu", help="") -main_arg_parser.add_argument("--model_filters", type=str, default="[32, 64, 128, 64]", help="") -main_arg_parser.add_argument("--model_classes", type=int, default=2, help="") -main_arg_parser.add_argument("--model_lat_dim", type=int, default=128, help="") -main_arg_parser.add_argument("--model_bias", type=strtobool, default=True, help="") -main_arg_parser.add_argument("--model_norm", type=strtobool, default=True, help="") -main_arg_parser.add_argument("--model_dropout", type=float, default=0.2, help="") - # Project Parameters main_arg_parser.add_argument("--project_name", type=str, default=_ROOT.name, help="") main_arg_parser.add_argument("--project_owner", type=str, default='si11ium', help="") diff --git a/main_inference.py b/main_inference.py index 2480f14..9a034c3 100644 --- a/main_inference.py +++ b/main_inference.py @@ -7,6 +7,7 @@ import variables as V from torch.utils.data import DataLoader, Dataset from torchvision.transforms import Compose, RandomApply +from ml_lib.audio_toolset.audio_augmentation import Speed from ml_lib.audio_toolset.audio_io import AudioToMel, NormalizeLocal, MelToImage # Dataset and Dataloaders @@ -17,6 +18,7 @@ from ml_lib.audio_toolset.mel_augmentation import NoiseInjection, LoudnessManipu from ml_lib.utils.logging import Logger from ml_lib.utils.model_io import SavedLightningModels from ml_lib.utils.transforms import ToTensor +from ml_lib.visualization.tools import Plotter from util.config import MConfig # Datasets @@ -25,23 +27,21 @@ from datasets.binar_masks import BinaryMasksDataset def prepare_dataloader(config_obj): mel_transforms = Compose([ - # Audio to Mel Transformations + Speed(0, 0), AudioToMel(sr=config_obj.data.sr, n_mels=config_obj.data.n_mels, n_fft=config_obj.data.n_fft, - hop_length=config_obj.data.hop_length), MelToImage()]) + hop_length=config_obj.data.hop_length), + MelToImage()]) transforms = Compose([NormalizeLocal(), ToTensor()]) aug_transforms = Compose([ - RandomApply([ - NoiseInjection(config_obj.data.noise_ratio), - LoudnessManipulator(config_obj.data.loudness_ratio), - ShiftTime(config_obj.data.shift_ratio), - MaskAug(config_obj.data.mask_ratio), - ], p=0.6), - # Utility + NoiseInjection(0.4), + LoudnessManipulator(0.4), + ShiftTime(0.3), + MaskAug(0.2), NormalizeLocal(), ToTensor() ]) dataset: Dataset = BinaryMasksDataset(config_obj.data.root, setting='train', - mel_transforms=mel_transforms, transforms=transforms + mel_transforms=mel_transforms, transforms=aug_transforms ) # noinspection PyTypeChecker return DataLoader(dataset, batch_size=None, num_workers=0, shuffle=False) @@ -69,6 +69,13 @@ if __name__ == '__main__': config = MConfig() config.read_file((outpath / model_type / parameters / version / config_filename).open('r')) test_dataloader = prepare_dataloader(config) + p = Plotter(outpath) + from matplotlib import pyplot as plt + + d = test_dataloader.dataset[100][0].squeeze() + plt.imshow(d) + p.save_current_figure('100') + loaded_model = restore_logger_and_model(config) loaded_model.eval() diff --git a/util/metric_reader.py b/util/metric_reader.py index 3cf1968..60b0f15 100644 --- a/util/metric_reader.py +++ b/util/metric_reader.py @@ -12,6 +12,8 @@ config_file_name = 'config.ini' if __name__ == '__main__': for model_path in outpath.iterdir(): + if not model_path.is_dir(): + continue out_file = (model_path / metric_file_name) for paramter_configuration in model_path.iterdir(): uar_scores = defaultdict(list) @@ -46,5 +48,8 @@ if __name__ == '__main__': writer = csv.DictWriter(f, delimiter=',', lineterminator='\n', fieldnames=headers) if not file_existed: writer.writeheader() # file doesn't exist yet, write a header - for row_idx in range(len(uar_scores['mean'])): - writer.writerow({key: uar_scores[key][row_idx] for key in headers}) + try: + for row_idx in range(len(uar_scores['mean'])): + writer.writerow({key: uar_scores[key][row_idx] for key in headers}) + except IndexError: + print('could not read: ') \ No newline at end of file