analyze_cmd.add_argument("--dataset", type=str, default='/home-nfs/tawara/work/ttic/MyPython/src/timit/timit_3.test.npz',
help="Which dataset to use")
rng = numpy.random.RandomState(1)
args = ap.parse_args()
t_start = time.time()
if args.cmd == 'analyze':
batchsize = args.batchsize
filename = args.load_from
print "load from %s" % filename
model = pickle.load(open(filename,'rb'))
model.device_id = [0]
cuda.get_device(0).use()
offset = range(-context_length, context_length+1)
x_test, frame_index = load_timit_labelled_kaldi(\
KaldiArk('/data2/tawara/work/ttic/MyPython/src/kaldi/timit/feats_test_cmvn.ark'), \
nnet_transf = '/data2/tawara/work/ttic/MyPython/src/kaldi/timit/final.feature_transform')
x_train,_ = load_data(\
KaldiScp('/data2/tawara/work/ttic/MyPython/src/kaldi/timit/data/fbank/train_tr90/feats.scp'), \
offsets = offset)
N_test=x_test.shape[0]
N_train=x_train.shape[0]
print "Applying batch normalization"
for i in xrange(0, N_train, batchsize):
x_batch = x_train[i : i + batchsize]
model.forward(x_batch,test=False)
logger.info("Extracting final layer")
save_to = args.save_to
print 'Saving output layer to %s' % filename+'.post.ark'
ark=KaldiArk(filename+'.post.ark','wb')
with open('timit/triplets') as cv:
tbl = {i:[int(p),int(s)] for p,s,i,_ in csv.reader(cv,delimiter=' ')}
phones=[]
states=[]
for value in y:
phones.append(tbl[str(value)][0])
tmp=[]
for value in y:
tmp.append(str(tbl[str(value)][0])+'_'+str(tbl[str(value)][1]))
d={}
cnt =0
for value in tmp:
if not d.has_key(value):
d[value] = cnt
cnt += 1
states.append(d[value])
res={}
res['phones']=np.asarray(phones, dtype=np.int32)
res['states']=np.asarray(states, dtype=np.int32)
return res
if __name__ == "__main__":
x_train_lb, y_train_lb = load_timit_labelled_kaldi('fbank/train_tr90_lb10', 'models/pdf.ark', nnet_transf = 'models/final.feature_transform')
print convert(y_train_lb)['phones'][0:10]
print convert(y_train_lb)['states'][0:10]
print len(set(convert(y_train_lb)['phones'])),len(set(convert(y_train_lb)['states']))