def load_river_network(nnet_param = 'neural_network/river_network_params', nnet_cfg = 'neural_network/river_network_cfg'):
cfg = cPickle.load(smart_open(nnet_cfg,'r'))
cfg.init_activation()
model = DNN(numpy_rng=numpy_rng, cfg = cfg)
_file2nnet(model.layers, filename = nnet_param)
get_river_probs = model.build_extract_feat_function(-1)
return get_river_probs
log('> ... setting up the model and loading parameters')
numpy_rng = np.random.RandomState(89677)
theano_rng = RandomStreams(numpy_rng.randint(2**30))
cfg_dnn = cPickle.load(open(filename, 'r'))
cfg_dnn.init_activation()
model = DNN(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg_dnn)
# load model parameters
_file2nnet(model.layers, filename=wdir + '/rbm.param')
# initialize data reading
cfg_dnn.init_data_reading_test(train_data_spec)
# get the function for feature extraction
log('> ... getting the feat-extraction function')
extract_func = model.build_extract_feat_function(-1)
output_mat = None # store the features for all the data in memory
log('> ... generating features from the specified layer')
while (not cfg_dnn.test_sets.is_finish()): # loop over the data
cfg_dnn.test_sets.load_next_partition(cfg_dnn.test_xy)
batch_num = int(math.ceil(cfg_dnn.test_sets.cur_frame_num / batch_size))
for batch_index in xrange(batch_num): # loop over mini-batches
start_index = batch_index * batch_size
end_index = min((batch_index + 1) * batch_size,
cfg_dnn.test_sets.cur_frame_num
) # the residue may be smaller than a mini-batch
output = extract_func(cfg_dnn.test_x.get_value()[start_index:end_index])
if output_mat is None:
output_mat = output
log('> ... model type: %s' % cfg.model_type)
if cfg.model_type == 'DNN':
model = DNN(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg)
elif cfg.model_type == 'CNN':
model = CNN(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg)
elif cfg.model_type == 'DNNV':
model = DNNV(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg)
elif cfg.model_type == 'CNNV':
model = CNNV(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg)
# load model parameters
_file2nnet(model.layers, filename=nnet_param)
# get the function for feature extraction
log('> ... getting the feat-extraction function')
extract_func = model.build_extract_feat_function(layer_index)
kaldiread = KaldiReadIn(in_scp_file)
kaldiwrite = KaldiWriteOut(out_ark_file)
log('> ... processing the data')
utt_number = 0
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 = extract_func(in_matrix)
kaldiwrite.write_kaldi_mat(uttid, out_matrix)
utt_number += 1
if utt_number % 100 == 0:
log('> ... processed %d utterances' % (utt_number))
cfg.init_activation()
model = None
if cfg.model_type == 'DNN':
model = DNN(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg)
elif cfg.model_type == 'CNN':
model = CNN(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg, testing = True)
# load model parameters
_file2nnet(model.layers, filename = nnet_param)
# initialize data reading
cfg.init_data_reading_test(data_spec)
# get the function for feature extraction
log('> ... getting the feat-extraction function')
extract_func = model.build_extract_feat_function(layer_index)
output_mats = [] # store the features for all the data in memory. TODO: output the features in a streaming mode
log('> ... generating features from the specified layer')
while (not cfg.test_sets.is_finish()): # loop over the data
cfg.test_sets.load_next_partition(cfg.test_xy)
batch_num = int(math.ceil(1.0 * cfg.test_sets.cur_frame_num / batch_size))
for batch_index in xrange(batch_num): # loop over mini-batches
start_index = batch_index * batch_size
end_index = min((batch_index+1) * batch_size, cfg.test_sets.cur_frame_num) # the residue may be smaller than a mini-batch
output = extract_func(cfg.test_x.get_value()[start_index:end_index])
output_mats.append(output)
output_mat = numpy.concatenate(output_mats)
log('> ... setting up the model and loading parameters')
numpy_rng = np.random.RandomState(89677)
theano_rng = RandomStreams(numpy_rng.randint(2 ** 30))
cfg_dnn = cPickle.load(open(filename,'r'))
cfg_dnn.init_activation()
model = DNN(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg_dnn)
# load model parameters
_file2nnet(model.layers, filename = wdir + '/rbm.param')
# initialize data reading
cfg_dnn.init_data_reading_test(train_data_spec)
# get the function for feature extraction
log('> ... getting the feat-extraction function')
extract_func = model.build_extract_feat_function(-1)
output_mat = None # store the features for all the data in memory
log('> ... generating features from the specified layer')
while (not cfg_dnn.test_sets.is_finish()): # loop over the data
cfg_dnn.test_sets.load_next_partition(cfg_dnn.test_xy)
batch_num = int(math.ceil(cfg_dnn.test_sets.cur_frame_num / batch_size))
for batch_index in xrange(batch_num): # loop over mini-batches
start_index = batch_index * batch_size
end_index = min((batch_index+1) * batch_size, cfg_dnn.test_sets.cur_frame_num) # the residue may be smaller than a mini-batch
output = extract_func(cfg_dnn.test_x.get_value()[start_index:end_index])
if output_mat is None:
output_mat = output
else:
output_mat = np.concatenate((output_mat, output)) # this is not efficient
def main(arg_elements):
# check the arguments
arguments = parse_arguments(arg_elements)
required_arguments = [
'data', 'nnet_param', 'nnet_cfg', 'output_file', 'layer_index',
'batch_size'
]
for arg in required_arguments:
if arguments.has_key(arg) == False:
print "Error: the argument %s has to be specified" % (arg)
exit(1)
# mandatory arguments
data_spec = arguments['data']
nnet_param = arguments['nnet_param']
nnet_cfg = arguments['nnet_cfg']
output_file = arguments['output_file']
layer_index = int(arguments['layer_index'])
batch_size = int(arguments['batch_size'])
argmax = arguments.has_key('argmax') and string2bool(arguments['argmax'])
# load network configuration and set up the model
log('> ... setting up the model and loading parameters')
numpy_rng = numpy.random.RandomState(89677)
theano_rng = RandomStreams(numpy_rng.randint(2**30))
cfg = cPickle.load(smart_open(nnet_cfg, 'r'))
cfg.init_activation()
model = None
if cfg.model_type == 'DNN':
model = DNN(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg)
elif cfg.model_type == 'CNN':
model = CNN(numpy_rng=numpy_rng,
theano_rng=theano_rng,
cfg=cfg,
testing=True)
# load model parameters
_file2nnet(model.layers, filename=nnet_param)
# initialize data reading
cfg.init_data_reading_test(data_spec)
# get the function for feature extraction
log('> ... getting the feat-extraction function')
extract_func = model.build_extract_feat_function(layer_index)
output_mats = [
] # store the features for all the data in memory. TODO: output the features in a streaming mode
log('> ... generating features from the specified layer')
while (not cfg.test_sets.is_finish()): # loop over the data
cfg.test_sets.load_next_partition(cfg.test_xy)
batch_num = int(
math.ceil(1.0 * cfg.test_sets.cur_frame_num / batch_size))
for batch_index in xrange(batch_num): # loop over mini-batches
start_index = batch_index * batch_size
end_index = min((batch_index + 1) * batch_size,
cfg.test_sets.cur_frame_num
) # the residue may be smaller than a mini-batch
output = extract_func(
cfg.test_x.get_value()[start_index:end_index])
output_mats.append(output)
output_mat = numpy.concatenate(output_mats)
if argmax:
output_mat = output_mat.argmax(axis=1)
# output the feature representations using pickle
f = smart_open(output_file, 'wb')
cPickle.dump(output_mat, f, cPickle.HIGHEST_PROTOCOL)
log('> ... the features are stored in ' + output_file)
