sHardVoteFile = os.path.join(sMajorVoteDir, 'hard.csv')
sSoftVoteFile = os.path.join(sMajorVoteDir, 'soft.csv')
if os.path.exists(sHardVoteFile) and os.path.exists(sSoftVoteFile):
majorVotesHard = np.genfromtxt(sHardVoteFile, delimiter=',')
majorVotesSoft = np.genfromtxt(sSoftVoteFile, delimiter=',')
else:
(majorVotesHard,
majorVotesSoft) = computeMajorVotes(sHardVoteFile, sSoftVoteFile,
sResultDir)
mProb = majorVotesSoft[:, 1:].copy()
print mProb.sum(1)
assert np.all(abs(mProb.sum(1) - config.CLASSIFIERS) < 1E-2)
mProb /= mProb.sum(1)[:, None]
kaldiOut = KaldiWriteOut(output_scp, output_ark)
kaldiOut.open()
rIdx = 0
for i, uId in enumerate(uttIDs):
kaldiOut.write(uId, mProb[rIdx:(rIdx + uttLens[i]), :])
rIdx += uttLens[i]
kaldiOut.close()
# write dummy weights (identity matrix)
with open(sWeightFile, 'wb') as fOut:
w = np.eye(mProb.shape[1])
(sz1, sz2) = w.shape
fOut.write('<affinetransform> %d %d\n[\n' % (sz2, sz1))
for c in xrange(0, sz2):
fOut.write(' '.join([str(w[r, c]) for r in xrange(0, sz1)]) + '\n')
fOut.write(']\n')
# run majorityVote, compute "probabilities"
sHardVoteFile = os.path.join(sMajorVoteDir, 'hard.csv')
sSoftVoteFile = os.path.join(sMajorVoteDir, 'soft.csv')
if os.path.exists(sHardVoteFile) and os.path.exists(sSoftVoteFile):
majorVotesHard = np.genfromtxt(sHardVoteFile, delimiter=',')
majorVotesSoft = np.genfromtxt(sSoftVoteFile, delimiter=',')
else:
(majorVotesHard, majorVotesSoft) = computeMajorVotes(sHardVoteFile, sSoftVoteFile, sResultDir)
mProb = majorVotesSoft[:, 1:].copy()
print mProb.sum(1)
assert np.all(abs(mProb.sum(1) - config.CLASSIFIERS) < 1E-2)
mProb /= mProb.sum(1)[:, None]
kaldiOut = KaldiWriteOut(output_scp, output_ark)
kaldiOut.open()
rIdx = 0
for i, uId in enumerate(uttIDs):
kaldiOut.write(uId, mProb[rIdx:(rIdx + uttLens[i]), :])
rIdx += uttLens[i]
kaldiOut.close()
# write dummy weights (identity matrix)
with open(sWeightFile, 'wb') as fOut:
w = np.eye(mProb.shape[1])
(sz1, sz2) = w.shape
fOut.write('<affinetransform> %d %d\n[\n' % (sz2, sz1))
for c in xrange(0, sz2):
fOut.write(' '.join([str(w[r, c]) for r in xrange(0, sz1)]) + '\n')
fOut.write(']\n')
sModelFile = arguments['model_file']
sDeeplearnPath = arguments['deeplearn_path']
# paths for output files
output_scp = output_file_prefix + '.scp'
output_ark = output_file_prefix + '.ark'
removeFile(output_scp)
removeFile(output_ark)
sDataDir = os.path.join(wdir, 'data')
if not os.path.exists(sDataDir):
os.mkdir(sDataDir)
kaldiIn = KaldiReadIn(ark_file)
kaldiIn.open()
kaldiOut = KaldiWriteOut(output_scp,output_ark)
kaldiOut.open()
uttIDBatch = []
uttIDLength = []
featMatBatch = None
batchSz = -1
uttID, featMat = kaldiIn.next()
while featMat is not None:
if batchSz < 0:
batchSz = 300*1024*1024 / (4*featMat.shape[1])
if featMatBatch is None:
featMatBatch = featMat
else:
featMatBatch = np.vstack([featMatBatch, featMat])
uttIDBatch.append(uttID)
sModelFile = arguments['model_file']
sDeeplearnPath = arguments['deeplearn_path']
# paths for output files
output_scp = output_file_prefix + '.scp'
output_ark = output_file_prefix + '.ark'
removeFile(output_scp)
removeFile(output_ark)
sDataDir = os.path.join(wdir, 'data')
if not os.path.exists(sDataDir):
os.mkdir(sDataDir)
kaldiIn = KaldiReadIn(ark_file)
kaldiIn.open()
kaldiOut = KaldiWriteOut(output_scp, output_ark)
kaldiOut.open()
uttIDBatch = []
uttIDLength = []
featMatBatch = None
batchSz = -1
uttID, featMat = kaldiIn.next()
while featMat is not None:
if batchSz < 0:
batchSz = 300 * 1024 * 1024 / (4 * featMat.shape[1])
if featMatBatch is None:
featMatBatch = featMat
else:
featMatBatch = np.vstack([featMatBatch, featMat])
uttIDBatch.append(uttID)