def __init__(self, scp_file, utt2label_file, M):
'Initialization'
self.M = M
self.scp_file = scp_file
self.utt2len = ako.read_key_len(scp_file)
self.utt2label = ako.read_key_label(utt2label_file)
self.feat_gen = ko.read_mat_scp(scp_file) # feature generator
self.utt2mat = {}
for key, mat in self.feat_gen:
self.utt2mat[key] = mat
def __init__(self, scp_file, utt2label_file):
'Initialization'
self.scp_file = scp_file
self.utt2label = ako.read_key_label(utt2label_file)
self.feat_gen = ko.read_mat_scp(scp_file) # feature generator
mats, labels = [], [] # construct feature and label matrices
for key, mat in self.feat_gen:
mats.append(mat)
labels.append(np.repeat(self.utt2label[key], len(mat)))
self.label_mat = np.hstack(labels)
self.feat_mat = np.vstack(mats)
def __init__(self, scp_file, utt2label_file):
'Initialization'
self.scp_file = scp_file
self.utt2label = ako.read_key_label(utt2label_file)
self.key_list = ako.read_all_key(scp_file)
from __future__ import print_function import adv_kaldi_io as ako test_scp = '/export/b19/jlai/cstr/spoof/baseline/v1/data/train_cqcc/feats.scp' test_utt2label = '/export/b19/jlai/cstr/spoof/baseline/v1/data/train_cqcc/utt2label' test_key = 'M0001-T_1000027' all_key = ako.read_all_key(test_scp) mat = ako.read_mat_key(test_scp, test_key) length = ako.read_total_len(test_scp) print(length) # 938016 label = ako.read_key_label(test_utt2label) key_map = ako.read_key_len(test_scp) print(key_map)
evaluation_scp = '/export/b19/jlai/cstr/spoof/model/src/data_reader/spec/eval_spec_cmvn_tensor.scp'
params = {'batch_size': 32,
'shuffle': False,
'num_workers': 0}
max_epochs = 1
training_set, validation_set, evaluation_set = SpoofDataset(train_scp, train_utt2label), SpoofDataset(validation_scp, validation_utt2label), SpoofDataset(evaluation_scp, evaluation_utt2label)
training_generator = data.DataLoader(training_set, **params)
validation_generator = data.DataLoader(validation_set, **params)
evaluation_generator = data.DataLoader(evaluation_set, **params)
validation_generator2 = data.DataLoader(validation_set, **params)
dev_utt2label = ako.read_key_label(validation_utt2label)
eval_utt2label = ako.read_key_label(evaluation_utt2label)
gen_1, gen_2 = {}, {}
for epoch in range(max_epochs):
for i_batch, sample_batched in enumerate(validation_generator):
#key = sample_batched[0][0]
#label = dev_utt2label[key]
gen_1[i_batch] = sample_batched[1]
if i_batch == 10: break
for i_batch, sample_batched in enumerate(validation_generator2):
#key = sample_batched[0][0]
#label = dev_utt2label[key]
gen_2[i_batch] = sample_batched[1]
if i_batch == 10: break
for i,value in gen_1.items():