from tables import *
import config
import utils
from spectrogram import Spectrogram
conf = config.get_config()
winsize = int(conf.get('Spectrogram', 'WindowSize'))
nframes = int(conf.get('Tracks', 'LengthInSeconds')) * \
int(conf.get('Tracks', 'SampleRate'))
stepsize = int(conf.get('Spectrogram', 'StepSize'))
fftres = int(conf.get('Spectrogram', 'FFTResolution'))
audio_folder = os.path.expanduser(conf.get('Input', 'AudioFolder'))
numberofgenres = len(utils.list_subdirs(audio_folder))
wins = Spectrogram.wins(winsize, nframes, stepsize)
bins = Spectrogram.bins(fftres)
shape = Spectrogram.shape(wins, bins)
class Track(IsDescription):
"""Description of a track in HDF5"""
idnumber = Int32Col()
name = StringCol(64)
path = StringCol(512)
genre = StringCol(32)
# target = BoolCol(shape=(numberofgenres,))
target = Int8Col()
spectrogram = Float32Col(dflt=0.0, shape=shape)
def __init__(self, path, which_set,
feature="spectrogram",
space="conv2d",
axes=('b', 0, 1, 'c'),
preprocess=False,
seconds=None,
window_size=None,
window_type=None,
step_size=None,
tw_window_size=None,
tw_window_type=None,
tw_step_size=None,
fft_resolution=None,
seed=None,
n_folds=4,
run_n=0,
verbose=False,
print_params=True):
super(AudioDataset, self).__init__()
converter = space
# signal is 1D
if feature == "signal":
space = "vector"
converter = "signal"
# inverting a spectrogram if the space is a vector doesn't make sense
if space == "vector" and feature == "inv_spectrogram":
feature == "spectrogram"
feature_extractors = {
"spectrogram": self.get_spectrogram_data,
"inv_spectrogram": self.get_inv_spectrogram_data,
"texture_window": self.get_texture_window_data,
"signal": self.get_signal_data
}
spaces_converters = {
"conv2d": AudioDataset.twod_to_conv2dspaces,
"vector": AudioDataset.twod_to_vectorspaces,
"signal": lambda x: x
}
index_converters = {
"conv2d": lambda x: x,
"vector": self.track_ids_to_frame_ids,
"signal": lambda x: x
}
path = string_utils.preprocess(path)
# init dynamic params
tracks, genres = self.tracks_and_genres(path, seconds)
samplerate = tracks[0].samplerate
seconds = tracks[0].seconds
if feature != "signal":
spec_wins_per_track = len(
Spectrogram.wins(
seconds * samplerate,
window_size,
step_size
)
)
if feature == "texture_window":
tw_wins_per_track = len(
TextureWindow.wins(
spec_wins_per_track,
tw_window_size,
tw_step_size
)
)
wins_per_track = tw_wins_per_track
else:
wins_per_track = spec_wins_per_track
bins_per_track = Spectrogram.bins(fft_resolution)
view_converters = {
"conv2d": dense_design_matrix.DefaultViewConverter(
(bins_per_track, wins_per_track, 1), axes
),
"vector": None,
"signal": None
}
view_converter = view_converters[converter]
self.__dict__.update(locals())
del self.self
if print_params:
print(self)