def eval_svm(iv_file, class2int_file, test_file,
preproc_file,
model_file, score_file, vector_score_file,
eval_type, **kwargs):
if preproc_file is not None:
preproc = TransformList.load(preproc_file)
else:
preproc = None
tdr_args = TDR.filter_args(**kwargs)
tdr = TDR(iv_file, class2int_file, test_file, preproc, **tdr_args)
x, ndx = tdr.read()
model = SVM.load(model_file)
t1 = time.time()
scores = model.predict(x, eval_type)
dt = time.time() - t1
num_trials = scores.shape[0]*scores.shape[1]
logging.info('Elapsed time: %.2f s. Elapsed time per trial: %.2f ms.'
% (dt, dt/num_trials*1000))
s = TrialScores(ndx.model_set, ndx.seg_set, scores.T)
s.save(score_file)
if vector_score_file is not None:
h5 = HDW(vector_score_file)
h5.write(ndx.seg_set, '', scores)
def eval_plda(iv_file, ndx_file, enroll_file, test_subseg2orig_file,
preproc_file,
model_file, score_file, plda_type,
**kwargs):
logging.info('loading data')
if preproc_file is not None:
preproc = TransformList.load(preproc_file)
else:
preproc = None
tdr = TDR(iv_file, ndx_file, enroll_file, None, test_subseg2orig_file, preproc)
x_e, x_t, enroll, ndx, orig_seg = tdr.read()
logging.info('loading plda model: %s' % (model_file))
model = F.load_plda(plda_type, model_file)
t1 = time.time()
logging.info('computing llr')
scores = model.llr_1vs1(x_e, x_t)
dt = time.time() - t1
num_trials = len(enroll) * x_t.shape[0]
logging.info('scoring elapsed time: %.2f s. elapsed time per trial: %.2f ms.'
% (dt, dt/num_trials*1000))
logging.info('combine cluster scores')
scores = combine_diar_scores(ndx, orig_seg, scores)
logging.info('saving scores to %s' % (score_file))
s = TrialScores(enroll, ndx.seg_set, scores)
s = s.align_with_ndx(ndx)
s.save_txt(score_file)
def eval_plda(iv_file, ndx_file, enroll_file, test_file, preproc_file,
model_file, score_file, pool_method, **kwargs):
if preproc_file is not None:
preproc = TransformList.load(preproc_file)
else:
preproc = None
tdr_args = TDR.filter_args(**kwargs)
tdr = TDR(iv_file, ndx_file, enroll_file, test_file, preproc, **tdr_args)
x_e, x_t, enroll, ndx = tdr.read()
enroll, ids_e = np.unique(enroll, return_inverse=True)
model = F.load_plda(plda_type, model_file)
t1 = time.time()
scores = model.llr_Nvs1(x_e, x_t, method=pool_method, ids1=ids_e)
dt = time.time() - t1
num_trials = len(enroll) * x_t.shape[0]
logging.info('Elapsed time: %.2f s. Elapsed time per trial: %.2f ms.' %
(dt, dt / num_trials * 1000))
s = TrialScores(enroll, ndx.seg_set, scores)
s.save(score_file)
def eval_plda(iv_file, ndx_file, enroll_file, test_file,
preproc_file,
model_file, score_file, plda_type, **kwargs):
if preproc_file is not None:
preproc = TransformList.load(preproc_file)
else:
preproc = None
tdr_args = TDR.filter_args(**kwargs)
tdr = TDR(iv_file, ndx_file, enroll_file, test_file, preproc, **tdr_args)
x_e, x_t, enroll, ndx = tdr.read()
model = F.load_plda(plda_type, model_file)
t1 = time.time()
scores = model.llr_1vs1(x_e, x_t)
dt = time.time() - t1
num_trials = x_e.shape[0] * x_t.shape[0]
logging.info('Elapsed time: %.2f s. Elapsed time per trial: %.2f ms.'
% (dt, dt/num_trials*1000))
s = TrialScores(enroll, ndx.seg_set, scores)
s.save(score_file)
def eval_cos(iv_file, ndx_file, enroll_file, test_file,
preproc_file, score_file, **kwargs):
if preproc_file is not None:
preproc = TransformList.load(preproc_file)
else:
preproc = None
tdr_args = TDR.filter_args(**kwargs)
tdr = TDR(iv_file, ndx_file, enroll_file, test_file, preproc, **tdr_args)
x_e, x_t, enroll, ndx = tdr.read()
lnorm = LNorm()
x_e = lnorm.predict(x_e)
x_t = lnorm.predict(x_t)
t1 = time.time()
scores = np.dot(x_e, x_t.T)
dt = time.time() - t1
num_trials = x_e.shape[0] * x_t.shape[0]
logging.info('Elapsed time: %.2f s. Elapsed time per trial: %.2f ms.'
% (dt, dt/num_trials*1000))
s = TrialScores(enroll, ndx.seg_set, scores)
s.save(score_file)
def eval_plda(iv_file, ndx_file, enroll_file, test_subseg2orig_file,
preproc_file, coh_iv_file, coh_list, coh_nbest,
coh_nbest_discard, model_file, score_file, plda_type, **kwargs):
logging.info('loading data')
if preproc_file is not None:
preproc = TransformList.load(preproc_file)
else:
preproc = None
tdr = TDR(iv_file, ndx_file, enroll_file, None, test_subseg2orig_file,
preproc)
x_e, x_t, enroll, ndx, orig_seg = tdr.read()
logging.info('loading plda model: %s' % (model_file))
model = F.load_plda(plda_type, model_file)
t1 = time.time()
logging.info('computing llr')
scores = model.llr_1vs1(x_e, x_t)
dt = time.time() - t1
num_trials = len(enroll) * x_t.shape[0]
logging.info(
'scoring elapsed time: %.2f s. elapsed time per trial: %.2f ms.' %
(dt, dt / num_trials * 1000))
logging.info('loading cohort data')
vr = VR(coh_iv_file, coh_list, preproc)
x_coh = vr.read()
t2 = time.time()
logging.info('score cohort vs test')
scores_coh_test = model.llr_1vs1(x_coh, x_t)
logging.info('score enroll vs cohort')
scores_enr_coh = model.llr_1vs1(x_e, x_coh)
dt = time.time() - t2
logging.info('cohort-scoring elapsed time: %.2f s.' % (dt))
t2 = time.time()
logging.info('apply s-norm')
snorm = SNorm(nbest=coh_nbest, nbest_discard=coh_nbest_discard)
scores = snorm.predict(scores, scores_coh_test, scores_enr_coh)
dt = time.time() - t2
logging.info('s-norm elapsed time: %.2f s.' % (dt))
dt = time.time() - t1
logging.info(
('total-scoring elapsed time: %.2f s. '
'elapsed time per trial: %.2f ms.') % (dt, dt / num_trials * 1000))
logging.info('combine cluster scores')
scores = combine_diar_scores(ndx, orig_seg, scores)
logging.info('saving scores to %s' % (score_file))
s = TrialScores(enroll, ndx.seg_set, scores)
s = s.align_with_ndx(ndx)
s.save_txt(score_file)
def create_scores(key_file='./tests/data_in/core-core_det5_key.h5'):
key = TrialKey.load(key_file)
mask = np.logical_or(key.tar, key.non)
scr1 = TrialScores(key.model_set, key.seg_set,
np.random.normal(size=key.tar.shape) * mask, mask)
return scr1, key
def test_filter():
scr1 = create_scores()[0]
scr1.sort()
scr2 = TrialScores(scr1.model_set[:5], scr1.seg_set[:10],
scr1.scores[:5, :10], scr1.score_mask[:5, :10])
scr3 = scr1.filter(scr2.model_set, scr2.seg_set, keep=True)
assert (scr2 == scr3)
def test_merge():
scr1 = create_scores()[0]
scr1.sort()
scr2 = TrialScores(scr1.model_set[:10], scr1.seg_set, scr1.scores[:10, :],
scr1.score_mask[:10, :])
scr3 = TrialScores(scr1.model_set[10:], scr1.seg_set, scr1.scores[10:, :],
scr1.score_mask[10:, :])
scr4 = TrialScores.merge([scr2, scr3])
assert (scr1 == scr4)
scr2 = TrialScores(scr1.model_set, scr1.seg_set[:10], scr1.scores[:, :10],
scr1.score_mask[:, :10])
scr3 = TrialScores(scr1.model_set, scr1.seg_set[10:], scr1.scores[:, 10:],
scr1.score_mask[:, 10:])
scr4 = TrialScores.merge([scr2, scr3])
assert (scr1 == scr4)
def convert(input_file, output_file, class_file):
r = DRF.create(input_file)
seg_set, score_mat = r.read(0, squeeze=True)
with open(class_file, 'r') as f:
model_set = [line.rstrip().split()[0] for line in f]
scores = TrialScores(model_set, seg_set, score_mat.T)
scores.save(output_file)
def eval_pdda(iv_file, ndx_file, enroll_file, test_file,
preproc_file,
model_file, score_file,
pool_method, eval_method,
num_samples_y, num_samples_z, num_samples_elbo, qy_only,
**kwargs):
set_float_cpu('float32')
if preproc_file is not None:
preproc = TransformList.load(preproc_file)
else:
preproc = None
tdr_args = TDR.filter_args(**kwargs)
tdr = TDR(iv_file, ndx_file, enroll_file, test_file, preproc, **tdt_args)
x_e, x_t, enroll, ndx = tdr.read()
enroll, ids_e = np.unique(enroll, return_inverse=True)
if qy_only:
model = TVAEY.load(model_file)
model.build(max_seq_length=2, num_samples=num_samples_y)
else:
model = TVAEYZ.load(model_file)
model.build(max_seq_length=2,
num_samples_y=num_samples_y, num_samples_z=num_samples_z)
t1 = time.time()
scores = model.eval_llr_Nvs1(x_e, ids_e, x_t,
pool_method=pool_method,
eval_method=eval_method,
num_samples=num_samples_elbo)
dt = time.time() - t1
num_trials = len(enroll) * x_t.shape[0]
logging.info('Elapsed time: %.2f s. Elapsed time per trial: %.2f ms.' %
(dt, dt/num_trials*1000))
s = TrialScores(enroll, ndx.seg_set, scores)
s.save(score_file)