Model Init

.gitignore

@@ -0,0 +1,5 @@
+# my own stuff
+
+/data
+/.idea
+/ml_lib

datasets/binar_masks.py

@@ -0,0 +1,53 @@
+from collections import defaultdict
+from pathlib import Path
+
+import librosa as librosa
+from torch.utils.data import Dataset
+
+import variables as V
+
+
+class BinaryMasks(Dataset):
+    _to_label = defaultdict(-1)
+    _to_label['clear'] = V.CLEAR
+    _to_label['mask'] = V.MASK
+
+    def __init__(self, data_root, setting):
+        assert isinstance(setting, str)
+        assert setting in ['test', 'devel', 'train']
+        super(BinaryMasks, self).__init__()
+
+        self.data_root = Path(data_root)
+        self.setting = setting
+        self._labels = self._build_labels()
+        self._wav_folder = self.data_root / 'wav'
+        self._files = list(sorted(self._labels.keys()))
+
+    def _build_labels(self):
+        with open(Path(self.data_root) / 'lab' / 'labels.csv', mode='r') as f:
+            # Exclude the header
+            _ = next(f)
+            labeldict = dict()
+            for row in f:
+                if self.setting not in row:
+                    continue
+                filename, label = row.split(',')
+                labeldict[filename] = self._to_label[label.lower()]
+        return labeldict
+
+    def __len__(self):
+        return len(self._labels)
+
+    def __getitem__(self, item):
+        key = self._files[item]
+        sample = librosa.core.load(self._wav_folder / self._files[key])
+        label = self._labels[key]
+        return sample, label
+
+
+
+
+
+
+
+

main.py

@@ -0,0 +1,141 @@
+# Imports
+# =============================================================================
+import os
+from distutils.util import strtobool
+from pathlib import Path
+from argparse import ArgumentParser, Namespace
+
+import warnings
+
+import torch
+from pytorch_lightning import Trainer
+from pytorch_lightning.callbacks import ModelCheckpoint, EarlyStopping
+from torch.utils.data import DataLoader
+
+from ml_lib.modules.utils import LightningBaseModule
+from ml_lib.utils.config import Config
+from ml_lib.utils.logging import Logger
+from ml_lib.utils.model_io import SavedLightningModels
+
+warnings.filterwarnings('ignore', category=FutureWarning)
+warnings.filterwarnings('ignore', category=UserWarning)
+
+_ROOT = Path(__file__).parent
+
+# Parameter Configuration
+# =============================================================================
+# Argument Parser
+main_arg_parser = ArgumentParser(description="parser for fast-neural-style")
+
+# Main Parameters
+main_arg_parser.add_argument("--main_debug", type=strtobool, default=False, help="")
+main_arg_parser.add_argument("--main_eval", type=strtobool, default=True, help="")
+main_arg_parser.add_argument("--main_seed", type=int, default=69, help="")
+
+# Data Parameters
+main_arg_parser.add_argument("--data_worker", type=int, default=10, help="")
+main_arg_parser.add_argument("--data_dataset_length", type=int, default=10000, help="")
+main_arg_parser.add_argument("--data_root", type=str, default='data', help="")
+main_arg_parser.add_argument("--data_normalized", type=strtobool, default=True, help="")
+main_arg_parser.add_argument("--data_use_preprocessed", type=strtobool, default=True, help="")
+
+# Transformation Parameters
+main_arg_parser.add_argument("--transformations_to_tensor", type=strtobool, default=False, 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="")
+main_arg_parser.add_argument("--train_epochs", type=int, default=500, help="")
+main_arg_parser.add_argument("--train_batch_size", type=int, default=200, help="")
+main_arg_parser.add_argument("--train_lr", type=float, default=1e-3, 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="BinaryClassifier", help="")
+main_arg_parser.add_argument("--model_activation", type=str, default="leaky_relu", help="")
+main_arg_parser.add_argument("--model_filters", type=str, default="[16, 32, 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=16, help="")
+main_arg_parser.add_argument("--model_use_bias", type=strtobool, default=True, help="")
+main_arg_parser.add_argument("--model_use_norm", type=strtobool, default=False, help="")
+main_arg_parser.add_argument("--model_dropout", type=float, default=0.00, help="")
+
+# Project Parameters
+main_arg_parser.add_argument("--project_name", type=str, default=_ROOT.parent.name, help="")
+main_arg_parser.add_argument("--project_owner", type=str, default='si11ium', help="")
+main_arg_parser.add_argument("--project_neptune_key", type=str, default=os.getenv('NEPTUNE_KEY'), help="")
+
+# Parse it
+args: Namespace = main_arg_parser.parse_args()
+
+
+def run_lightning_loop(config_obj):
+
+    # Logging
+    # ================================================================================
+    # Logger
+    with Logger(config_obj) as logger:
+        # Callbacks
+        # =============================================================================
+        # Checkpoint Saving
+        checkpoint_callback = ModelCheckpoint(
+            filepath=str(logger.log_dir / 'ckpt_weights'),
+            verbose=True, save_top_k=0,
+        )
+
+        # =============================================================================
+        # Early Stopping
+        # TODO: For This to work, set a validation step and End Eval and Score
+        early_stopping_callback = EarlyStopping(
+            monitor='val_loss',
+            min_delta=0.0,
+            patience=0,
+        )
+
+        # Dataset and Dataloaders
+        # =============================================================================
+        # Train Dataset
+        from datasets.binar_masks import BinaryMasks
+        dataset = BinaryMasks(config_obj.data.root, setting='train')
+        # Train Dataloader
+        dataloader = DataLoader(dataset)
+
+        # Model
+        # =============================================================================
+        # Build and Init its Weights
+        model: LightningBaseModule = config_obj.build_and_init_model(weight_init_function=torch.nn.init.xavier_normal_)
+
+        # Trainer
+        # =============================================================================
+        trainer = Trainer(max_epochs=config_obj.train.epochs,
+                          show_progress_bar=True,
+                          weights_save_path=logger.log_dir,
+                          gpus=[0] if torch.cuda.is_available() else None,
+                          check_val_every_n_epoch=10,
+                          # num_sanity_val_steps=config_obj.train.num_sanity_val_steps,
+                          # row_log_interval=(model.n_train_batches * 0.1),  # TODO: Better Value / Setting
+                          # log_save_interval=(model.n_train_batches * 0.2),  # TODO: Better Value / Setting
+                          checkpoint_callback=checkpoint_callback,
+                          logger=logger,
+                          fast_dev_run=config_obj.main.debug,
+                          early_stop_callback=None
+                          )
+
+        # Train It
+        trainer.fit(model)
+
+        # Save the last state & all parameters
+        trainer.save_checkpoint(logger.log_dir / 'weights.ckpt')
+        model.save_to_disk(logger.log_dir)
+
+        # Evaluate It
+        if config_obj.main.eval:
+            trainer.test()
+
+    return model
+
+
+if __name__ == "__main__":
+
+    config = Config.read_namespace(args)
+    trained_model = run_lightning_loop(config)

models/binary_classifier.py

@@ -0,0 +1,47 @@
+import torch
+from torch import nn
+from torch.optim import Adam
+
+from ml_lib.modules.blocks import ConvModule
+from ml_lib.modules.utils import LightningBaseModule
+
+
+class BinaryClassifier(LightningBaseModule):
+    @classmethod
+    def name(cls):
+        return cls.__name__
+
+    def configure_optimizers(self):
+        return Adam(lr=self.hparams.train.lr)
+
+    def training_step(self, batch_xy, batch_nb, *args, **kwargs):
+        batch_x, batch_y = batch_xy
+        y = self(batch_y)
+        loss = self.criterion(y, batch_y)
+        return dict(loss=loss)
+
+    def validation_step(self, batch_xy, **kwargs):
+        batch_x, batch_y = batch_xy
+        y = self(batch_y)
+        val_loss = self.criterion(y, batch_y)
+        return dict(val_loss=val_loss)
+
+    def validation_epoch_end(self, outputs):
+        over_all_val_loss = torch.mean(torch.stack([output['val_loss'] for output in outputs]))
+
+    def __init__(self, hparams):
+        super(BinaryClassifier, self).__init__(hparams)
+        self.criterion = nn.BCELoss()
+
+        # Additional parameters
+        self.in_shape = ()
+
+        # Model Modules
+        self.conv_1 = ConvModule(self.in_shape, 32, 5, )
+        self.conv_2 = ConvModule(64)
+        self.conv_3 = ConvModule(128)
+
+    def forward(self, batch, **kwargs):
+        return batch
+
+

variables.py

@@ -0,0 +1,3 @@
+# Labels
+CLEAR = 0
+MASK = 1