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
#
# need to access the files where we perform the estimation
#
utterances_path = '/home/mark/Template-Speech-Recognition/Data/Train/'
file_indices = gtrd.get_data_files_indices(utterances_path)
inner_mask = np.zeros((5,5),dtype=np.uint8)
inner_mask[1:-1,1:-1] = 1
all_patches = np.zeros((0,5,5,8),dtype=np.uint8)
all_S_patches = np.zeros((0,5,5),dtype=np.float32)
inner_thresh = 9
outer_thresh = 40
for fl_idx,fl in enumerate(file_indices[:50]):
utterance = gtrd.makeUtterance(utterances_path,fl)
S = gtrd.get_spectrogram(utterance.s,sp)
E = gtrd.get_edge_features(S.T,ep,verbose=False)
patch_set, S_patch_set, patch_counts, patch_locs = cp.get_parts_mask(E.astype(np.uint8),
inner_mask,
S.astype(np.float32),
inner_thresh)
use_patch_ids = patch_set.sum(-1).sum(-1).sum(-1) >= outer_thresh
all_patches = np.vstack(
(all_patches,
patch_set[use_patch_ids ]))
all_S_patches = np.vstack(
(all_S_patches,
S_patch_set[use_patch_ids].astype(np.float32)))
fl = file_indices[49]