def read_data_args(data_spec):
elements = data_spec.split(",")
pfile_path_list = glob.glob(elements[0])
dataset_args = {}
# default settings
dataset_args['type'] = 'pickle'
dataset_args['random'] = False
dataset_args['stream'] = False
dataset_args['utt'] = False # True: use utterance feature
dataset_args['partition'] = 1024 * 1024 * 600 # by default the partition size is 600m if stream is True
dataset_args['lcxt'] = 0
dataset_args['rcxt'] = 0
# the type of the data: pickle, pfile TO-DO: HDF5
if '.pickle' in data_spec or '.pkl' in data_spec:
dataset_args['type'] = 'pickle'
elif '.pfile' in data_spec:
dataset_args['type'] = 'pfile'
elif '.scp' in data_spec:
dataset_args['type'] = 'kaldi'
else:
dataset_args['type'] = ''
for i in range(1, len(elements)):
element = elements[i]
arg_value = element.split("=")
value = arg_value[1]
key = arg_value[0]
if key == 'partition':
dataset_args['partition'] = 1024 * 1024 * int(value.replace('m',''))
elif key == 'stream':
dataset_args['stream'] = string2bool(value) # not supported for now
elif key == 'random':
dataset_args['random'] = string2bool(value)
elif key == 'label':
dataset_args['label'] = value
elif key == 'lcxt':
dataset_args['lcxt'] = int(value)
elif key == 'rcxt':
dataset_args['rcxt'] = int(value)
elif key == 'context':
value = tuple(int(x) for x in value.split(':'))
if len(value) == 1: value += value
dataset_args['lcxt'], dataset_args['rcxt'] = value
elif key == 'ignore-label':
dataset_args['ignore-label'] = parse_ignore_label(value)
elif key == 'map-label':
dataset_args['map-label'] = parse_map_label(value)
elif key == 'utt':
dataset_args['utt'] = string2bool(value)
else:
dataset_args[key] = value
if dataset_args['utt'] == False:
print("Don't use utterance save!")
#assert len(pfile_path_list)==1
#print(pfile_path_list)
return pfile_path_list, dataset_args
def read_data_args(data_spec):
elements = data_spec.split(",")
log("data argument = "+str(elements))
pfile_path_list = sorted(glob.glob(elements[0]))
log("Found = "+str(pfile_path_list))
dataset_args = {}
# default settings
dataset_args['type'] = 'pickle'
dataset_args['random'] = False
dataset_args['stream'] = False
dataset_args['partition'] = 1024 * 1024 * 600 # by default the partition size is 600m if stream is True
dataset_args['lcxt'] = 0
dataset_args['rcxt'] = 0
# the type of the data: pickle, pfile TO-DO: HDF5
if '.pickle' in data_spec or '.pkl' in data_spec:
dataset_args['type'] = 'pickle'
elif '.blp' in data_spec:
dataset_args['type'] = 'blocspack'
elif '.pfile' in data_spec:
dataset_args['type'] = 'pfile'
elif '.scp' in data_spec:
dataset_args['type'] = 'kaldi'
else:
dataset_args['type'] = ''
for i in range(1, len(elements)):
element = elements[i]
arg_value = element.split("=")
value = arg_value[1]
key = arg_value[0]
if key == 'partition':
dataset_args['partition'] = 1024 * 1024 * int(value.replace('m',''))
elif key == 'stream':
dataset_args['stream'] = string2bool(value) # not supported for now
elif key == 'random':
dataset_args['random'] = string2bool(value)
elif key == 'label':
dataset_args['label'] = value
elif key == 'lcxt':
dataset_args['lcxt'] = int(value)
elif key == 'rcxt':
dataset_args['rcxt'] = int(value)
elif key == 'context':
value = tuple(int(x) for x in value.split(':'))
if len(value) == 1: value += value
dataset_args['lcxt'], dataset_args['rcxt'] = value
elif key == 'ignore-label':
dataset_args['ignore-label'] = parse_ignore_label(value)
elif key == 'map-label':
dataset_args['map-label'] = parse_map_label(value)
else:
dataset_args[key] = value
return pfile_path_list, dataset_args
in_scp_file = arguments['in_scp_file']
out_ark_file = arguments['out_ark_file']
cnn_param_file = arguments['cnn_param_file']
cnn_cfg_file = arguments['cnn_cfg_file']
# network structure
cfg = cPickle.load(smart_open(cnn_cfg_file, 'r'))
conv_configs = cfg.conv_layer_configs
conv_layer_number = len(conv_configs)
for i in xrange(conv_layer_number):
conv_configs[i]['activation'] = cfg.conv_activation
# whether to use the fast mode
use_fast = cfg.use_fast
if arguments.has_key('use_fast'):
use_fast = string2bool(arguments['use_fast'])
kaldiread = KaldiReadIn(in_scp_file)
kaldiwrite = KaldiWriteOut(out_ark_file)
log('> ... setting up the CNN convolution layers')
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,
# check the arguments
arg_elements = [sys.argv[i] for i in range(1, len(sys.argv))]
arguments = parse_arguments(arg_elements)
required_arguments = ['data', 'nnet_param', 'nnet_cfg', 'output_file', 'layer_index', 'batch_size']
for arg in required_arguments:
if (arg in arguments) == 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 = float(arguments['batch_size'])
argmax = 'argmax' in arguments and string2bool(arguments['argmax'])
log("Extracting in batches with size="+str(batch_size))
if batch_size == -1:
log("Extracting all features per partition at once")
# 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 = pickle.load(smart_open(nnet_cfg,'rb'))
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)
'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)
in_scp_file = arguments['in_scp_file']
out_ark_file = arguments['out_ark_file']
cnn_param_file = arguments['cnn_param_file']
cnn_cfg_file = arguments['cnn_cfg_file']
# network structure
cfg = cPickle.load(smart_open(cnn_cfg_file,'r'))
conv_configs = cfg.conv_layer_configs
conv_layer_number = len(conv_configs)
for i in xrange(conv_layer_number):
conv_configs[i]['activation'] = cfg.conv_activation
# whether to use the fast mode
use_fast = cfg.use_fast
if arguments.has_key('use_fast'):
use_fast = string2bool(arguments['use_fast'])
kaldiread = KaldiReadIn(in_scp_file)
kaldiwrite = KaldiWriteOut(out_ark_file)
log('> ... setting up the CNN convolution layers')
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()
# check the arguments
arg_elements = [sys.argv[i] for i in range(1, len(sys.argv))]
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 = float(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)
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)
