cfg_si.init_data_reading(train_data_spec, valid_data_spec)
# parse the structure of the i-vector network
cfg_adapt = NetworkConfig()
net_split = adapt_nnet_spec.split(':')
adapt_nnet_spec = ''
for n in xrange(len(net_split) - 1):
adapt_nnet_spec += net_split[n] + ':'
cfg_adapt.parse_config_dnn(arguments, adapt_nnet_spec + '0')
numpy_rng = numpy.random.RandomState(89677)
theano_rng = RandomStreams(numpy_rng.randint(2**30))
log('> ... initializing the model')
# setup up the model
dnn = CNN_SAT(numpy_rng=numpy_rng,
theano_rng=theano_rng,
cfg_si=cfg_si,
cfg_adapt=cfg_adapt)
# read the initial DNN (the SI DNN which has been well trained)
# _file2nnet(dnn.cnn_si.layers, filename = init_model_file)
_file2nnet(dnn.cnn_si.layers, filename='BKUP/nnet.param.si')
_file2nnet(dnn.dnn_adapt.layers, filename='BKUP/nnet.param.adapt')
# get the training and validation functions for adaptation network training
dnn.params = dnn.dnn_adapt.params # only update the parameters of the i-vector nnet
dnn.delta_params = dnn.dnn_adapt.delta_params
log('> ... getting the finetuning functions for iVecNN')
train_fn, valid_fn = dnn.build_finetune_functions(
(cfg_si.train_x, cfg_si.train_y), (cfg_si.valid_x, cfg_si.valid_y),
batch_size=cfg_adapt.batch_size)
log('> ... learning the adaptation network')
cfg_si.parse_config_cnn(arguments, '10:' + si_nnet_spec, si_conv_nnet_spec)
cfg_si.init_data_reading(train_data_spec, valid_data_spec)
# parse the structure of the i-vector network
cfg_adapt = NetworkConfig()
net_split = adapt_nnet_spec.split(':')
adapt_nnet_spec = ''
for n in range(len(net_split) - 1):
adapt_nnet_spec += net_split[n] + ':'
cfg_adapt.parse_config_dnn(arguments, adapt_nnet_spec + '0')
numpy_rng = numpy.random.RandomState(89677)
theano_rng = RandomStreams(numpy_rng.randint(2 ** 30))
log('> ... initializing the model')
# setup up the model
dnn = CNN_SAT(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg_si = cfg_si, cfg_adapt = cfg_adapt)
# read the initial DNN (the SI DNN which has been well trained)
# _file2nnet(dnn.cnn_si.layers, filename = init_model_file)
_file2nnet(dnn.cnn_si.layers, filename = 'BKUP/nnet.param.si')
_file2nnet(dnn.dnn_adapt.layers, filename = 'BKUP/nnet.param.adapt')
# get the training and validation functions for adaptation network training
dnn.params = dnn.dnn_adapt.params # only update the parameters of the i-vector nnet
dnn.delta_params = dnn.dnn_adapt.delta_params
log('> ... getting the finetuning functions for iVecNN')
train_fn, valid_fn = dnn.build_finetune_functions(
(cfg_si.train_x, cfg_si.train_y), (cfg_si.valid_x, cfg_si.valid_y),
batch_size = cfg_adapt.batch_size)
log('> ... learning the adaptation network')
cfg = cfg_adapt
train_dataset, train_dataset_args = read_data_args(train_data_spec)
valid_dataset, valid_dataset_args = read_data_args(valid_data_spec)
# reading data
train_sets, train_xy, train_x, train_y = read_dataset(train_dataset, train_dataset_args)
valid_sets, valid_xy, valid_x, valid_y = read_dataset(valid_dataset, valid_dataset_args)
numpy_rng = numpy.random.RandomState(89677)
theano_rng = RandomStreams(numpy_rng.randint(2 ** 30))
log('> ... building the model')
# construct the cnn architecture
cnn = CNN_SAT(numpy_rng=numpy_rng, theano_rng = theano_rng,
batch_size = batch_size, n_outs=n_outs,
conv_layer_configs = conv_layer_configs,
hidden_layers_sizes = hidden_layers_sizes,
ivec_layers_sizes = ivec_layers_sizes,
conv_activation = conv_activation,
full_activation = full_activation,
use_fast = use_fast, update_part = update_part, ivec_dim = ivec_dim)
if arguments.has_key('conv_input_file'):
_file2cnn(cnn.conv_layers, filename=arguments['conv_input_file'])
if arguments.has_key('full_input_file'):
_file2nnet(cnn.full_layers, filename = arguments['full_input_file'])
if arguments.has_key('ivec_input_file'):
_file2nnet(cnn.ivec_layers, set_layer_num = len(ivec_layers_sizes) + 1, filename = arguments['ivec_input_file'], withfinal=False)
# get the training, validation and testing function for the model
log('> ... getting the finetuning functions')
train_fn, valid_fn = cnn.build_finetune_functions(
(train_x, train_y), (valid_x, valid_y),
