def _load_scaler(state):
scaler_state = state["scaler"]
type_sc = scaler_state["type"]
if type_sc == "ScalerPerAudio":
scaler = ScalerPerAudio(*scaler_state["args"])
elif type_sc == "Scaler":
scaler = Scaler()
else:
raise NotImplementedError("Not the right type of Scaler has been saved in state")
scaler.load_state_dict(state["scaler"]["state_dict"])
return scaler
# Meta path for psds
durations_synth = get_durations_df(cfg.synthetic)
many_hot_encoder = ManyHotEncoder(cfg.classes,
n_frames=cfg.max_frames //
pooling_time_ratio)
encod_func = many_hot_encoder.encode_strong_df
# Normalisation per audio or on the full dataset
if cfg.scaler_type == "dataset":
transforms = get_transforms(cfg.max_frames, add_axis=add_axis_conv)
weak_data = DataLoadDf(dfs["weak"], encod_func, transforms)
unlabel_data = DataLoadDf(dfs["unlabel"], encod_func, transforms)
train_synth_data = DataLoadDf(dfs["train_synthetic"], encod_func,
transforms)
scaler_args = []
scaler = Scaler()
# # Only on real data since that's our final goal and test data are real
scaler.calculate_scaler(
ConcatDataset([weak_data, unlabel_data, train_synth_data]))
logger.debug(f"scaler mean: {scaler.mean_}")
else:
scaler_args = ["global", "min-max"]
scaler = ScalerPerAudio(*scaler_args)
transforms = get_transforms(cfg.max_frames,
scaler,
add_axis_conv,
noise_dict_params={
"mean": 0.,
"snr": cfg.noise_snr
})