das.train_tune

Code for tuning the hyperparameters of a network.

class das.train_tune.DasTuner(params, *args, tracker=None, **kwargs)[source]
run_trial(trial, train_x, train_y, val_x=None, val_y=None, epochs=10, steps_per_epoch=None, verbose=1, class_weight=None, callbacks=None)[source]

Evaluates a set of hyperparameter values.

This method is called multiple times during search to build and evaluate the models with different hyperparameters and return the objective value.

Example:

You can use it with self.hypermodel to build and fit the model.

```python def run_trial(self, trial, *args, **kwargs):

hp = trial.hyperparameters model = self.hypermodel.build(hp) return self.hypermodel.fit(hp, model, *args, **kwargs)

```

You can also use it as a black-box optimizer for anything.

```python def run_trial(self, trial, *args, **kwargs):

hp = trial.hyperparameters x = hp.Float(“x”, -2.0, 2.0) y = x * x + 2 * x + 1 return y

```

Parameters
  • trial – A Trial instance that contains the information needed to run this trial. Hyperparameters can be accessed via trial.hyperparameters.

  • *args – Positional arguments passed by search.

  • **kwargs – Keyword arguments passed by search.

Returns

A History object, which is the return value of model.fit(), a dictionary, a float, or a list of one of these types.

If return a dictionary, it should be a dictionary of the metrics to track. The keys are the metric names, which contains the objective name. The values should be the metric values.

If return a float, it should be the objective value.

If evaluating the model for multiple times, you may return a list of results of any of the types above. The final objective value is the average of the results in the list.

class das.train_tune.ModelParamsCheckpoint(filepath, monitor='val_loss', verbose=0, save_best_only=False, save_weights_only=False, mode='auto', save_freq='epoch', options=None, **kwargs)[source]

Callback to save the DAS model or model weights and parameters at some frequency.

class das.train_tune.OracleCallback(tuner)[source]
on_epoch_end(epoch, logs=None)[source]

Called at the end of an epoch.

Subclasses should override for any actions to run. This function should only be called during TRAIN mode.

Parameters
  • epoch – Integer, index of epoch.

  • logs

    Dict, metric results for this training epoch, and for the

    validation epoch if validation is performed. Validation result keys are prefixed with val_. For training epoch, the values of the

    Model’s metrics are returned. Example`{‘loss’: 0.2, ‘accuracy’:

    0.7}`.

class das.train_tune.TunableModel(params, tune_config=None)[source]
build(hp)[source]

Builds a model.

Parameters

hp – A HyperParameters instance.

Returns

A model instance.

das.train_tune.train(*, data_dir: str, x_suffix: str = '', y_suffix: str = '', save_dir: str = './', save_prefix: Optional[str] = None, save_name: Optional[str] = None, model_name: str = 'tcn', nb_filters: int = 16, kernel_size: int = 16, nb_conv: int = 3, use_separable: List[bool] = False, nb_hist: int = 1024, ignore_boundaries: bool = True, batch_norm: bool = True, nb_pre_conv: int = 0, pre_nb_dft: int = 64, pre_kernel_size: int = 3, pre_nb_filters: int = 16, pre_nb_conv: int = 2, upsample: bool = True, dilations: Optional[List[int]] = None, nb_lstm_units: int = 0, verbose: int = 2, batch_size: int = 32, nb_epoch: int = 400, learning_rate: Optional[float] = None, reduce_lr: bool = False, reduce_lr_patience: int = 5, fraction_data: Optional[float] = None, seed: Optional[int] = None, batch_level_subsampling: bool = False, augmentations: Optional[str] = None, tensorboard: bool = False, wandb_api_token: Optional[str] = None, wandb_project: Optional[str] = None, wandb_entity: Optional[str] = None, log_messages: bool = False, nb_stacks: int = 2, with_y_hist: bool = True, balance: bool = False, version_data: bool = True, tune_config: Optional[str] = None, nb_tune_trials: int = 1000, _qt_progress: bool = False) Tuple[keras.engine.training.Model, Dict[str, Any]][source]

Tune the hyperparameters of a DAS network.

Parameters
  • data_dir (str) – Path to the directory or file with the dataset for training. Accepts npy-dirs (recommended), h5 files or zarr files. See documentation for how the dataset should be organized.

  • x_suffix (str) – Select dataset used for training in the data_dir by suffix (y_ + X_SUFFIX). Defaults to ‘’ (will use the standard data ‘x’)

  • y_suffix (str) – Select dataset used as a training target in the data_dir by suffix (y_ + Y_SUFFIX). Song-type specific targets can be created with a training dataset, Defaults to ‘’ (will use the standard target ‘y’)

  • save_dir (str) – Directory to save training outputs. The path of output files will constructed from the SAVE_DIR, an optional SAVE_PREFIX, and the time stamp of the start of training. Defaults to the current directory (‘./’).

  • save_prefix (Optional[str]) – Prepend to timestamp. Name of files created will be start with SAVE_DIR/SAVE_PREFIX + “_” + TIMESTAMP or with SAVE_DIR/TIMESTAMP if SAVE_PREFIX is empty. Defaults to ‘’ (empty).

  • save_name (Optional[str]) – Append to prefix. Name of files created will be start with SAVE_DIR/SAVE_PREFIX + “_” + SAVE_NAME or with SAVE_DIR/SAVE_NAME if SAVE_PREFIX is empty. Defaults to TIMESTAMP.

  • model_name (str) – Network architecture to use. Use tcn (TCN) or tcn_stft (TCN with STFT frontend). See das.models for a description of all models. Defaults to tcn.

  • nb_filters (int) – Number of filters per layer. Defaults to 16.

  • kernel_size (int) – Duration of the filters (=kernels) in samples. Defaults to 16.

  • nb_conv (int) – Number of TCN blocks in the network. Defaults to 3.

  • use_separable (List[bool]) – Specify which TCN blocks should use separable convolutions. Provide as a space-separated sequence of “False” or “True. For instance: “True False False” will set the first block in a three-block (as given by nb_conv) network to use separable convolutions. Defaults to False (no block uses separable convolutions).

  • nb_hist (int) – Number of samples processed at once by the network (a.k.a chunk duration). Defaults to 1024 samples.

  • ignore_boundaries (bool) – Minimize edge effects by discarding predictions at the edges of chunks. Defaults to True.

  • batch_norm (bool) – Batch normalize. Defaults to True.

  • nb_pre_conv (int) – Adds fronted with downsampling. The downsampling factor is 2**nb_pre_conv. The type of frontend depends on the model: if model is tcn: adds a frontend of N conv blocks (conv-relu-batchnorm-maxpool2) to the TCN. if model is tcn_tcn: adds a frontend of N TCN blocks to the TCN. if model is tcn_stft: adds a trainable STFT frontend. Defaults to 0 (no frontend, no downsampling).

  • pre_nb_dft (int) – Duration of filters (in samples) for the STFT frontend. Number of filters is pre_nb_dft // 2 + 1. Defaults to 64.

  • pre_nb_filters (int) – Number of filters per layer in the pre-processing TCN. Defaults to 16.

  • pre_kernel_size (int) – Duration of filters (=kernels) in samples in the pre-processing TCN. Defaults to 3.

  • upsample (bool) – whether or not to restore the model output to the input samplerate. Should generally be True during training and evaluation but my speed up inference. Defaults to True.

  • dilations (List[int]) – List of dilation rate, defaults to [1, 2, 4, 8, 16] (5 layer with 2x dilation per TCN block)

  • nb_lstm_units (int) – If >0, adds LSTM with nb_lstm_units LSTM units to the output of the stack of TCN blocks. Defaults to 0 (no LSTM layer).

  • verbose (int) – Verbosity of training output (0 - no output during training, 1 - progress bar, 2 - one line per epoch). Defaults to 2.

  • batch_size (int) – Batch size Defaults to 32.

  • nb_epoch (int) – Maximal number of training epochs. Training will stop early if validation loss did not decrease in the last 20 epochs. Defaults to 400.

  • learning_rate (Optional[float]) – Learning rate of the model. Defaults should work in most cases. Values typically range between 0.1 and 0.00001. If None, uses model specific defaults: tcn 0.0001, tcn_stft and tcn_tcn 0.0005. Defaults to None.

  • reduce_lr (bool) – Reduce learning rate when the validation loss plateaus. Defaults to False.

  • reduce_lr_patience (int) – Number of epochs w/o a reduction in validation loss after which to trigger a reduction in learning rate. Defaults to 5 epochs.

  • fraction_data (Optional[float]) – Fraction of training and validation data to use. Defaults to 1.0.

  • seed (Optional[int]) – Random seed to reproducibly select fractions of the data. Defaults to None (no seed).

  • batch_level_subsampling (bool) – Select fraction of data for training from random subset of shuffled batches. If False, select a continuous chunk of the recording. Defaults to False.

  • tensorboard (bool) – Write tensorboard logs to save_dir. Defaults to False.

  • wandb_api_token (Optional[str]) – API token for logging to wandb. Defaults to None (no logging to wandb).

  • wandb_project (Optional[str]) – Project to log to for wandb. Defaults to None (no logging to wandb).

  • wandb_entity (Optional[str]) – Entity to log to for wandb. Defaults to None (no logging to wandb).

  • log_messages (bool) – Sets terminal logging level to INFO. Defaults to False (will follow existing settings).

  • nb_stacks (int) – Unused if model name is tcn, tcn_tcn, or tcn_stft. Defaults to 2.

  • with_y_hist (bool) – Unused if model name is tcn, tcn_tcn, or tcn_stft. Defaults to True.

  • balance (bool) – Balance data. Weights class-wise errors by the inverse of the class frequencies. Defaults to False.

  • version_data (bool) – Save MD5 hash of the data_dir to log and params.yaml. Defaults to True (set to False for large datasets since it can be slow).

  • tune_config (Optional[str]) – Yaml file with key:value pairs defining the search space for tuning. Keys are parameter names, values are lists of possible parameter values.

  • nb_tune_trials (int) – Number of model variants to test during hyper parameter tuning. Defaults to 1_000.

  • Returns – model (keras.Model) params (Dict[str, Any])