steffen/masks_augments_compare-21
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master'

Browse Source 
# Conflicts:
#	_paramters.py
This commit is contained in:
Steffen Illium 2020-05-17 16:43:20 +02:00
commit 2462a76cc2
3 changed files with 39 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
_paramters.py
View File

@ -32,12 +32,24 @@ main_arg_parser.add_argument("--data_stretch", type=strtobool, default=True, hel
# Transformation Parameters # Transformation Parameters
main_arg_parser.add_argument("--data_loudness_ratio", type=float, default=0, help="") # 0.4 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_shift_ratio", type=float, default=0.3, help="") # 0.3
main_arg_parser.add_argument("--data_noise_ratio", type=float, default=0, help="") # 0.4 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_mask_ratio", type=float, default=0, help="") # 0.2
main_arg_parser.add_argument("--data_speed_ratio", type=float, default=0, help="") # 0.3 main_arg_parser.add_argument("--data_speed_ratio", type=float, default=0, help="") # 0.3
main_arg_parser.add_argument("--data_speed_factor", type=float, default=0, help="") # 0.7 main_arg_parser.add_argument("--data_speed_factor", type=float, default=0, 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 # Training Parameters
main_arg_parser.add_argument("--train_outpath", type=str, default="output", help="") main_arg_parser.add_argument("--train_outpath", type=str, default="output", help="")
main_arg_parser.add_argument("--train_version", type=strtobool, required=False, 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_lr", type=float, default=1e-4, help="")
main_arg_parser.add_argument("--train_num_sanity_val_steps", type=int, default=0, 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 # Project Parameters
main_arg_parser.add_argument("--project_name", type=str, default=_ROOT.name, help="") 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="") main_arg_parser.add_argument("--project_owner", type=str, default='si11ium', help="")

32
main_inference.py
View File

@ -7,6 +7,7 @@ import variables as V
from torch.utils.data import DataLoader, Dataset from torch.utils.data import DataLoader, Dataset
from torchvision.transforms import Compose, RandomApply 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 from ml_lib.audio_toolset.audio_io import AudioToMel, NormalizeLocal, MelToImage
# Dataset and Dataloaders # 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.logging import Logger
from ml_lib.utils.model_io import SavedLightningModels from ml_lib.utils.model_io import SavedLightningModels
from ml_lib.utils.transforms import ToTensor from ml_lib.utils.transforms import ToTensor
from ml_lib.visualization.tools import Plotter
from util.config import MConfig from util.config import MConfig
# Datasets # Datasets
@ -25,31 +27,27 @@ from datasets.binar_masks import BinaryMasksDataset
def prepare_dataloader(config_obj): def prepare_dataloader(config_obj):
mel_transforms = Compose([ mel_transforms = Compose([
# Audio to Mel Transformations
AudioToMel(sr=config_obj.data.sr, n_mels=config_obj.data.n_mels, n_fft=config_obj.data.n_fft, 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()]) transforms = Compose([NormalizeLocal(), ToTensor()])
aug_transforms = Compose([ aug_transforms = Compose([
RandomApply([ NoiseInjection(0.4),
NoiseInjection(config_obj.data.noise_ratio), LoudnessManipulator(0.4),
LoudnessManipulator(config_obj.data.loudness_ratio), ShiftTime(0.3),
ShiftTime(config_obj.data.shift_ratio), MaskAug(0.2),
MaskAug(config_obj.data.mask_ratio),
], p=0.6),
# Utility
NormalizeLocal(), ToTensor() NormalizeLocal(), ToTensor()
]) ])
dataset: Dataset = BinaryMasksDataset(config_obj.data.root, setting='train', dataset: Dataset = BinaryMasksDataset(config_obj.data.root, setting='test',
mel_transforms=mel_transforms, transforms=transforms mel_transforms=mel_transforms, transforms=transforms
) )
# noinspection PyTypeChecker # noinspection PyTypeChecker
return DataLoader(dataset, batch_size=None, num_workers=0, shuffle=False) return DataLoader(dataset, batch_size=None, num_workers=0, shuffle=False)
def restore_logger_and_model(config_obj): def restore_logger_and_model(log_dir):
logger = Logger(config_obj) model = SavedLightningModels.load_checkpoint(models_root_path=log_dir, n=-2)
model = SavedLightningModels.load_checkpoint(models_root_path=logger.log_dir, n=-2)
model = model.restore() model = model.restore()
if torch.cuda.is_available(): if torch.cuda.is_available():
model.cuda() model.cuda()
@ -63,16 +61,18 @@ if __name__ == '__main__':
model_type = 'CC' model_type = 'CC'
parameters = 'CC_213adb16e46592c5a405abfbd693835e/' parameters = 'CC_213adb16e46592c5a405abfbd693835e/'
version = 'version_41' version = 'version_41'
model_path = Path('/home/steffen/projects/inter_challenge_2020/output/CC/CC_fd2020a7ead9d5c80609a7364741f24b/version_40')
config_filename = 'config.ini' config_filename = 'config.ini'
inference_out = 'manual_test_out.csv' inference_out = 'manual_test_out.csv'
config = MConfig() config = MConfig()
config.read_file((outpath / model_type / parameters / version / config_filename).open('r')) config.read_file((Path(model_path) / config_filename).open('r'))
test_dataloader = prepare_dataloader(config) test_dataloader = prepare_dataloader(config)
loaded_model = restore_logger_and_model(config)
loaded_model = restore_logger_and_model(model_path)
loaded_model.eval() loaded_model.eval()
with (outpath / model_type / parameters / version / inference_out).open(mode='w') as outfile: with (model_path / inference_out).open(mode='w') as outfile:
outfile.write(f'file_name,prediction\n') outfile.write(f'file_name,prediction\n')
for batch in tqdm(test_dataloader, total=len(test_dataloader)): for batch in tqdm(test_dataloader, total=len(test_dataloader)):

13
util/metric_reader.py
View File

@ -12,8 +12,12 @@ config_file_name = 'config.ini'
if __name__ == '__main__': if __name__ == '__main__':
for model_path in outpath.iterdir(): for model_path in outpath.iterdir():
if not model_path.is_dir():
continue
out_file = (model_path / metric_file_name) out_file = (model_path / metric_file_name)
for paramter_configuration in model_path.iterdir(): for paramter_configuration in model_path.iterdir():
if not model_path.is_dir():
continue
uar_scores = defaultdict(list) uar_scores = defaultdict(list)
for metric_file in paramter_configuration.rglob(metric_file_name): for metric_file in paramter_configuration.rglob(metric_file_name):
with metric_file.open('r') as f: with metric_file.open('r') as f:
@ -35,7 +39,7 @@ if __name__ == '__main__':
metric_dict[header].append(value) metric_dict[header].append(value)
for score, func in zip(['mean', 'max', 'median', 'std'], [np.mean, np.max, np.median, np.std]): for score, func in zip(['mean', 'max', 'median', 'std'], [np.mean, np.max, np.median, np.std]):
try: try:
uar_scores[score].append(func(np.asarray(metric_dict['uar_score'])).round(2)) uar_scores[score].append(round(func(np.asarray(metric_dict['uar_score'])) * 100, 2))
except ValueError as e: except ValueError as e:
print(e) print(e)
pass pass
@ -46,5 +50,8 @@ if __name__ == '__main__':
writer = csv.DictWriter(f, delimiter=',', lineterminator='\n', fieldnames=headers) writer = csv.DictWriter(f, delimiter=',', lineterminator='\n', fieldnames=headers)
if not file_existed: if not file_existed:
writer.writeheader() # file doesn't exist yet, write a header writer.writeheader() # file doesn't exist yet, write a header
for row_idx in range(len(uar_scores['mean'])): try:
writer.writerow({key: uar_scores[key][row_idx] for key in headers}) 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: ')