def main():
desc = 'Extract features with DNN. Output to Kaldi ark.'
parser = common.init_argparse(desc)
parser.add_argument('model_in', help='Model that can be read by load_dnn')
parser.add_argument('feats_scp', help='scp of input features')
parser.add_argument('ark_out', help='Output ark file')
parser.add_argument('--output-layer', type=int, default=-2,
help='Layer to use for extracting features. ' + \
'Negative index can be used. For example, ' + \
'-1 means the last layer, and so on.')
parser.add_argument('--context',
type=int,
default=8,
help='Number of context frames for splicing')
parser.add_argument('--padding', default='replicate',
help='What to do with out-of-bound frames. Valid ' + \
'values: [replicate|zero]')
parser.add_argument('--ivectors', help='Utterance i-vectors to append')
parser.add_argument('--chunk-size',
default='300m',
help='Chunk size for data buffering')
args = parser.parse_args()
io.log('Initializing dataset')
ivectors = None if args.ivectors is None else \
io.ivector_ark_read(args.ivectors, dtype=theano.config.floatX)
dataset = init_dataset(args.feats_scp, args.context, args.padding,
ivectors)
io.log('Initializing model')
dnn = load_dnn(args.model_in)
# Initializing shared_ds according to chunk_size
num_items = get_num_items(args.chunk_size, theano.config.floatX)
max_frames = num_items / dataset.get_dim()
max_utt_frames = np.max(
map(dataset.get_num_frames_by_utt_name, dataset.get_utt_names()))
common.CHK_GE(max_frames, max_utt_frames)
x = np.zeros((max_frames, dataset.get_dim()), dtype=theano.config.floatX)
io.log('...getting extraction function')
extract_fn = dnn.build_extract_feat_function(args.output_layer)
io.log('Got it!')
io.log('** Begin outputting to {} **'.format(args.ark_out))
ark_out = KaldiWriteOut(args.ark_out)
utt_names, utt_frames, total_frames = [], [], 0
for utt in dataset.get_utt_names():
frames = dataset.get_num_frames_by_utt_name(utt)
if total_frames + frames > max_frames:
__extract(extract_fn, ark_out, dataset, x, utt_names, utt_frames)
utt_names, utt_frames, total_frames = [], [], 0
utt_names.append(utt)
utt_frames.append(frames)
total_frames += frames
__extract(extract_fn, ark_out, dataset, x, utt_names, utt_frames)
ark_out.close()
input_shape_train = conv_configs[0]['input_shape']
input_shape_1 = (input_shape_train[1], input_shape_train[2],
input_shape_train[3])
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2**30))
cnn = CNN_Forward(numpy_rng=rng,
theano_rng=theano_rng,
conv_layer_configs=conv_configs,
use_fast=use_fast)
_file2nnet(cnn.conv_layers,
set_layer_num=len(conv_configs),
filename=cnn_param_file)
out_function = cnn.build_out_function()
log('> ... processing the data')
while True:
uttid, in_matrix = kaldiread.read_next_utt()
if uttid == '':
break
in_matrix = numpy.reshape(in_matrix,
(in_matrix.shape[0], ) + input_shape_1)
out_matrix = out_function(in_matrix)
kaldiwrite.write_kaldi_mat(uttid, out_matrix)
kaldiwrite.close()
log('> ... the saved features are %s' % (out_ark_file))
rng = numpy.random.RandomState(89677)
theano_rng = RandomStreams(rng.randint(2 ** 30))
cfg.init_activation()
cnn = CNN_Forward(numpy_rng = rng, theano_rng=theano_rng, conv_layer_configs = conv_configs, use_fast = use_fast)
#cnn = CNNV(numpy_rng = rng, theano_rng=theano_rng, cfg=cfg)
_file2nnet(cnn.conv_layers, set_layer_num = len(conv_configs), filename=cnn_param_file)
out_function = cnn.build_out_function()
#out_function = cnn.build_extract_feat_function(-1)
#print cnn.conv_layers[1].filter_shape
model = DNNV(numpy_rng = rng, theano_rng = theano_rng, cfg = cfg, input=cnn.conv_layers[1].output)
_file2nnet(model.layers, set_layer_num = len(model.layers)+len(conv_configs), start_layer=len(conv_configs), filename=cnn_param_file)
log('> ... processing the data')
while True:
uttid, in_matrix = kaldiread.read_next_utt()
if uttid == '':
break
in_matrix = numpy.reshape(in_matrix, (in_matrix.shape[0],) + input_shape_1)
extract_function = model.build_extract_feat_function(layer_index)
mid_matrix = out_function(in_matrix)
out_matrix = extract_function(mid_matrix)
kaldiwrite.write_kaldi_mat(uttid, out_matrix)
kaldiwrite.close()
log('> ... the saved features are %s' % (out_ark_file))