def main(args):
if args.v:
print args
print "Checking value of args.useDefaultParams=", args.useDefaultParams
if args.useDefaultParams:
if args.v:
# retrieving params with function
print "Using default parameters"
(
sp,
ep,
root_path,
utterances_path,
file_indices,
num_mix_params,
test_path,
train_path,
train_example_lengths,
train_file_indices,
test_example_lengths,
test_file_indices,
) = get_params(args)
else:
# need to change this to something else
(
sp,
ep,
root_path,
utterances_path,
file_indices,
num_mix_params,
test_path,
train_path,
train_example_lengths,
train_file_indices,
test_example_lengths,
test_file_indices,
) = get_params(args)
file_indices = get_file_indices(args.fileIndicesPath, args.dataPath)
if args.limitFileIndices > -1:
if args.v:
print "Limiting file indices to length %d" % args.limitFileIndices
file_indices = file_indices[: args.limitFileIndices]
elif args.v:
print "No limit on file indices"
if args.partsPath != "":
if args.v:
print "Loading in parts from %s" % args.partsPath
EParts = np.clip(np.load(args.partsPath), 0.01, 0.99)
logParts = np.log(EParts).astype(np.float64)
logInvParts = np.log(1 - EParts).astype(np.float64)
if args.printEdgeDistribution:
edge_distribution = getEdgeDistribution(file_indices, args.hw, file_indices_chunks=args.file_indices_chunks)
elif args.edgeQuantileComparison != "":
for fl_id, fl in enumerate(file_indices):
if args.v:
print fl_id
utterance = gtrd.makeUtterance(args.dataPath, fl)
print sp, args.mel_smoothing_kernel
S = gtrd.get_spectrogram(utterance.s, sp, mel_smoothing_kernel=args.mel_smoothing_kernel)
E, edge_feature_row_breaks, edge_orientations = esp._edge_map_no_threshold(S.T)
E2 = np.empty((E.shape[0] / 8, E.shape[1], 8))
for i in xrange(8):
E2[:, :, i] = E[E.shape[0] / 8 * i : E.shape[0] / 8 * (i + 1), :]
print E2.shape, S.shape
visualize_spec_and_quantiles(
"%s_%d" % (args.edgeQuantileComparison, fl_id), E2, S, args.quantileSet, args.blockLengthSet
)
elif args.createBackgroundMixture > 0:
pass
elif args.getUnclippedBackground != "":
# initialize the background
if args.v:
print "Initializing average background to be computed over parts"
avg_bgd = gtrd.AverageBackground()
for fl_id, fl in enumerate(file_indices):
if args.v:
print fl_id
utterance = gtrd.makeUtterance(args.dataPath, fl)
print sp, args.mel_smoothing_kernel
S = gtrd.get_spectrogram(utterance.s, sp, mel_smoothing_kernel=args.mel_smoothing_kernel)
E = gtrd.get_edge_features(S.T, ep, verbose=False)
if args.seeBackgroundEstimatePlots != "":
visualize_edge_on_specs("%s_%d.png" % (args.seeBackgroundEstimatePlots, fl_id), E, S)
out = code_parts.code_parts(E.astype(np.uint8), logParts, logInvParts, args.bernsteinEdgeThreshold)
max_responses = np.argmax(out, -1)
if args.bernsteinPreSpreadVisualizeOnSpec != "":
# cycle over all parts
for part_id in xrange(logParts.shape[0]):
visualize_bern_on_specs(
"%s_%d_%d.png" % (args.bernsteinPreSpreadVisualizeOnSpec, fl_id, part_id),
max_responses,
S,
part_id,
)
bin_out_map = code_parts.spread_patches(max_responses, 2, 2, out.shape[-1] - 1)
avg_bgd.add_frames(bin_out_map, time_axis=0)
np.save(args.getUnclippedBackground, avg_bgd.E)
else:
pass
def save_syllable_features_to_data_dir(
args,
phn_tuple,
utterances_path,
file_indices,
sp,
ep,
phn_mapping,
tag_data_with_syllable_string=False,
save_tag="train",
waveform_offset=10,
block_features=False,
):
"""
Wrapper function to get all the examples processed
"""
print "Collecting the data for phn_tuple " + " ".join("%s" % k for k in phn_tuple)
syllable_string = "_".join(p for p in phn_tuple)
phn_features, avg_bgd = gtrd.get_syllable_features_directory(
utterances_path,
file_indices,
phn_tuple,
S_config=sp,
E_config=ep,
offset=0,
E_verbose=False,
return_avg_bgd=True,
waveform_offset=15,
phn_mapping=phn_mapping,
)
bgd = np.clip(avg_bgd.E, 0.01, 0.4)
np.save("data/bgd.npy", bgd)
example_mat = gtrd.recover_example_map(phn_features)
lengths, waveforms = gtrd.recover_waveforms(phn_features, example_mat)
if tag_data_with_syllable_string:
np.savez(
"data/%s_waveforms_lengths_%s.npz" % (syllable_string, save_tag),
waveforms=waveforms,
lengths=lengths,
example_mat=example_mat,
)
else:
np.savez(
"data/waveforms_lengths_%s.npz" % save_tag, waveforms=waveforms, lengths=lengths, example_mat=example_mat
)
Slengths, Ss = gtrd.recover_specs(phn_features, example_mat)
Ss = Ss.astype(np.float32)
if tag_data_with_syllable_string:
np.savez(
"data/%s_Ss_lengths_%s.npz" % (syllable_string, save_tag), Ss=Ss, Slengths=Slengths, example_mat=example_mat
)
else:
np.savez("data/Ss_lengths_%s.npz" % (save_tag), Ss=Ss, Slengths=Slengths, example_mat=example_mat)
Elengths, Es = gtrd.recover_edgemaps(phn_features, example_mat, bgd=bgd)
Es = Es.astype(np.uint8)
if tag_data_with_syllable_string:
np.savez(
"data/%s_Es_lengths_%s.npz" % (syllable_string, save_tag), Es=Es, Elengths=Elengths, example_mat=example_mat
)
else:
np.savez("data/Es_lengths_%s.npz" % (save_tag), Es=Es, Elengths=Elengths, example_mat=example_mat)
if args.doBlockFeatures:
out = code_parts.code_parts(E.astype(np.uint8), logParts, logInvParts, args.bernsteinEdgeThreshold)
max_responses = np.argmax(out, -1)
Bs = code_parts.spread_patches(max_responses, 2, 2, out.shape[-1] - 1)