def compute_edge_features(x,config_d):
S, sample_mapping, sample_to_frames = esp.get_spectrogram_features(x.astype(float)/(2**15-1),
config_d['SPECTROGRAM']['sample_rate'],
config_d['SPECTROGRAM']['num_window_samples'],
config_d['SPECTROGRAM']['num_window_step_samples'],
config_d['SPECTROGRAM']['fft_length'],
config_d['SPECTROGRAM']['freq_cutoff'],
config_d['SPECTROGRAM']['kernel_length'],
preemph=config_d['SPECTROGRAM']['preemphasis'],
no_use_dpss=config_d['SPECTROGRAM']['no_use_dpss'],
do_freq_smoothing=config_d['SPECTROGRAM']['do_freq_smoothing'],
return_sample_mapping=True
)
E, edge_feature_row_breaks,\
edge_orientations = esp._edge_map_no_threshold(S.T)
esp._edge_map_threshold_segments(E,
config_d['EDGES']['block_length'],
config_d['EDGES']['spread_length'],
threshold=config_d['EDGES']['threshold'],
edge_orientations = edge_orientations,
edge_feature_row_breaks = edge_feature_row_breaks,
abst_threshold=config_d['EDGES']['abst_threshold'],
verbose=False)
return reorg_part_for_fast_filtering(E).astype(np.uint8)
def get_waliji_feature_map(s,
log_part_blocks,
log_invpart_blocks,
abst_threshold=np.array([.025,.025,.015,.015,
.02,.02,.02,.02]),
spread_length=3,
fft_length=512,
num_window_step_samples=80,
freq_cutoff=3000,
sample_rate=16000,
num_window_samples=320,
kernel_length=7):
"""
Input is usually just the signal s as the rest of the parameters
are not going to change very often
Parameters:
===========
s: np.ndarray[ndim=1]
Raw signal data that we are extracting feature from
log_part_blocks: np.ndarray[ndim=4,dtype=np.float32]
First dimension is over the different features
log_invpart_blocks: np.ndarray[ndim=4,dtype=np.float32]
Essentially the same array as log_part_blocks. Related
by its equal to np.log(1-np.exp(log_part_blocks))
"""
S = esp.get_spectrogram_features(s,
sample_rate,
num_window_samples,
num_window_step_samples,
fft_length,
freq_cutoff,
kernel_length,
)
E, edge_feature_row_breaks,\
edge_orientations = esp._edge_map_no_threshold(S)
esp._edge_map_threshold_segments(E,
40,
1,
threshold=.7,
edge_orientations = edge_orientations,
edge_feature_row_breaks = edge_feature_row_breaks)
E = reorg_part_for_fast_filtering(E)
F = cp.code_parts_fast(E.astype(np.uint8),log_part_blocks,log_invpart_blocks,10)
F = np.argmax(F,2)
# the amount of spreading to do is governed by the size of the part features
F = swp.spread_waliji_patches(F,
log_part_blocks.shape[1],
log_part_blocks.shape[2],
log_part_blocks.shape[0])
return collapse_to_grid(F,log_part_blocks.shape[1],
log_part_blocks.shape[2])
s_idx_list = []
for s_idx, s_fname in enumerate(s_fnames[:400]):
print "s_idx = %d" %s_idx
f.write(str(s_idx)+'\t'+s_fname+'\n')
s = np.load(s_fname)
S = esp.get_spectrogram_features(s,
sample_rate,
num_window_samples,
num_window_step_samples,
fft_length,
freq_cutoff,
kernel_length)
if lower_cutoff == 10:
np.save(tmp_data_path+str(s_idx)+'S.npy',S)
E, edge_feature_row_breaks,\
edge_orientations = esp._edge_map_no_threshold(S)
esp._edge_map_threshold_segments(E,
20,
1,
threshold=.7,
edge_orientations = edge_orientations,
edge_feature_row_breaks = edge_feature_row_breaks)
if lower_cutoff == 10:
np.save(tmp_data_path+str(s_idx)+'E.npy',E)
patch_width = 5
patch_height = 5
upper_cutoff = 200
bp,all_patch_rows,all_patch_cols = elf.extract_local_features_tied(E,patch_height,
patch_width, lower_cutoff,
upper_cutoff,
edge_feature_row_breaks,
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
