def _load_state_vars(state, gtruth_df, median_win=None):
pred_df = gtruth_df.copy()
# Define dataloader
many_hot_encoder = ManyHotEncoder.load_state_dict(
state["many_hot_encoder"])
scaler = _load_scaler(state)
crnn = _load_crnn(state)
transforms_valid = get_transforms(cfg.max_frames,
scaler=scaler,
add_axis=0)
strong_dataload = DataLoadDf(pred_df,
many_hot_encoder.encode_strong_df,
transforms_valid,
return_indexes=True)
strong_dataloader_ind = DataLoader(strong_dataload,
batch_size=cfg.batch_size,
drop_last=False)
pooling_time_ratio = state["pooling_time_ratio"]
many_hot_encoder = ManyHotEncoder.load_state_dict(
state["many_hot_encoder"])
if median_win is None:
median_win = state["median_window"]
return {
"model": crnn,
"dataloader": strong_dataloader_ind,
"pooling_time_ratio": pooling_time_ratio,
"many_hot_encoder": many_hot_encoder,
"median_window": median_win
}
def _load_state_vars(state, gtruth_df, median_win=None):
pred_df = gtruth_df.copy()
# Define dataloader
many_hot_encoder = ManyHotEncoder.load_state_dict(state["many_hot_encoder"])
scaler = _load_scaler(state)
crnn = _load_crnn(state)
# Note, need to unsqueeze axis 1
transforms_valid = get_transforms(cfg.max_frames, scaler=scaler, add_axis=1)
# Note, no dataloader here
strong_dataload = DataLoadDf(pred_df, many_hot_encoder.encode_strong_df, transforms_valid, return_indexes=True)
pooling_time_ratio = state["pooling_time_ratio"]
many_hot_encoder = ManyHotEncoder.load_state_dict(state["many_hot_encoder"])
if median_win is None:
median_win = state["median_window"]
return {
"model": crnn,
"dataload": strong_dataload,
"pooling_time_ratio": pooling_time_ratio,
"many_hot_encoder": many_hot_encoder,
"median_window": median_win
}
# ##############
dataset = DESED(base_feature_dir=os.path.join(cfg.workspace, "dataset",
"features"),
compute_log=False)
dfs = get_dfs(dataset, reduced_number_of_data)
# 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,
