for bias in biases:
f.write(str(bias) + "\n")
# Arguments for this script
parser = argparse.ArgumentParser()
parser.add_argument("-m", "--corelm-model", dest="corelm_model", required=True, help="The input NPLM model file")
parser.add_argument("-v", "--vocab-file", dest="vocab_path", required=True, help="The input vocabulary")
parser.add_argument("-dir", "--directory", dest="out_dir", help="The output directory for log file, model, etc.")
args = parser.parse_args()
U.set_theano_device('cpu',1)
from dlm.models.mlp import MLP
if args.out_dir is None:
args.out_dir = 'corelm_convert-' + U.curr_time()
U.mkdir_p(args.out_dir)
# Loading CoreLM model and creating classifier class
L.info("Loading CoreLM model")
classifier = MLP(model_path=args.corelm_model)
args_nn = classifier.args
params_nn = classifier.params
U.xassert(len(params_nn)==7, "CoreLM model is not compatible with NPLM architecture. 2 hidden layers and an output linear layer is required.")
embeddings = params_nn[0].get_value()
W1 = params_nn[1].get_value()
W1 = np.transpose(W1)
b1 = params_nn[2].get_value()
W2 = params_nn[3].get_value()
W2 = np.transpose(W2)
# Arguments for this script
parser = argparse.ArgumentParser()
parser.add_argument("-m", "--nplm-model", dest="nplm_model", required=True, help="The input NPLM model file")
parser.add_argument("-dir", "--directory", dest="out_dir", help="The output directory for log file, model, etc.")
args = parser.parse_args()
U.set_theano_device('cpu',1)
from dlm.models.mlp import MLP
if args.out_dir is None:
args.out_dir = 'nplm_convert-' + U.curr_time()
U.mkdir_p(args.out_dir)
# Reading the NPLM Model
args_nn = argparse.Namespace()
model_dict = dict()
lines = []
req_attribs = ['\config','\\vocab', '\input_vocab', '\output_vocab', '\input_embeddings', '\hidden_weights 1', '\hidden_biases 1', '\hidden_weights 2', '\hidden_biases 2', '\output_weights', '\output_biases','\end']
attrib = ''
with open(args.nplm_model,'r') as f_model:
for line in f_model:
line = line.strip()
if(line in req_attribs):
if attrib != '':
for bias in biases:
f.write(str(bias) + "\n")
# Arguments for this script
parser = argparse.ArgumentParser()
parser.add_argument("-m", "--primelm-model", dest="primelm_model", required=True, help="The input NPLM model file")
parser.add_argument("-v", "--vocab-file", dest="vocab_path", required=True, help="The input vocabulary")
parser.add_argument("-dir", "--directory", dest="out_dir", help="The output directory for log file, model, etc.")
args = parser.parse_args()
U.set_theano_device('cpu',1)
from dlm.models.mlp import MLP
if args.out_dir is None:
args.out_dir = 'primelm_convert-' + U.curr_time()
U.mkdir_p(args.out_dir)
# Loading PrimeLM model and creating classifier class
L.info("Loading PrimeLM model")
classifier = MLP(model_path=args.primelm_model)
args_nn = classifier.args
params_nn = classifier.params
U.xassert(len(params_nn)==7, "PrimeLM model is not compatible with NPLM architecture. 2 hidden layers and an output linear layer is required.")
embeddings = params_nn[0].get_value()
W1 = params_nn[1].get_value()
W1 = np.transpose(W1)
b1 = params_nn[2].get_value()
W2 = params_nn[3].get_value()
W2 = np.transpose(W2)
parser.add_argument("--clip-threshold", dest="clip_threshold", default=0, type=float, help="If threshold > 0, clips gradients to [-threshold, +threshold]. Default: 0 (disabled)")
parser.add_argument("--weighted-emb", dest="weighted_emb", action='store_true', help="Use this flag to add per-word weights to embeddings.")
parser.add_argument("--threads", dest="threads", default=8, type=int, help="Number of threads when device is CPU. Default: 8")
parser.add_argument("--emb-path", dest="emb_path", help="(optional) Word embeddings file.")
parser.add_argument("--vocab", dest="vocab", help="(optional) Only needed if --emb-path is used.")
parser.add_argument("--quiet", dest="quiet", action='store_true', help="Use this flag to disable the logger.")
parser.add_argument( "--adjust-learning-rate", dest="enable_lr_adjust", action='store_true', help="Enable learning rate adjustment")
#parser.add_argument("-m","--model-file", dest="model_path", help="The file path to load the model from")
args = parser.parse_args()
args.cwd = os.getcwd()
if args.out_dir is None:
args.out_dir = 'corelm-' + U.curr_time()
U.mkdir_p(args.out_dir)
L.quiet = args.quiet
L.set_file_path(os.path.abspath(args.out_dir) + "/log.txt")
L.info('Command: ' + ' '.join(sys.argv))
curr_version = U.curr_version()
if curr_version:
L.info("Version: " + curr_version)
if args.emb_path:
U.xassert(args.vocab, 'When --emb-path is used, vocab file must be given too (using --vocab).')
if args.loss_function == "nll":
"--vocab-file",
dest="vocab_path",
required=True,
help="The input vocabulary")
parser.add_argument("-dir",
"--directory",
dest="out_dir",
help="The output directory for log file, model, etc.")
args = parser.parse_args()
U.set_theano_device('cpu', 1)
from dlm.models.mlp import MLP
if args.out_dir is None:
args.out_dir = 'primelm_convert-' + U.curr_time()
U.mkdir_p(args.out_dir)
# Loading PrimeLM model and creating classifier class
L.info("Loading PrimeLM model")
classifier = MLP(model_path=args.primelm_model)
args_nn = classifier.args
params_nn = classifier.params
U.xassert(
len(params_nn) == 7,
"PrimeLM model is not compatible with NPLM architecture. 2 hidden layers and an output linear layer is required."
)
embeddings = params_nn[0].get_value()
W1 = params_nn[1].get_value()
W1 = np.transpose(W1)
dest="enable_lr_adjust",
action='store_true',
help="Enable learning rate adjustment")
parser.add_argument("-bm",
"--base-model",
dest="base_model_path",
help="Base model used for adaptation")
#parser.add_argument("-m","--model-file", dest="model_path", help="The file path to load the model from")
args = parser.parse_args()
args.cwd = os.getcwd()
if args.out_dir is None:
args.out_dir = 'primelm-' + U.curr_time()
U.mkdir_p(args.out_dir)
L.quiet = args.quiet
L.set_file_path(os.path.abspath(args.out_dir) + "/log.txt")
L.info('Command: ' + ' '.join(sys.argv))
curr_version = U.curr_version()
if curr_version:
L.info("Version: " + curr_version)
if args.emb_path:
U.xassert(
args.vocab,
'When --emb-path is used, vocab file must be given too (using --vocab).'
dest="quiet",
action='store_true',
help="Use this flag to disable the logger.")
parser.add_argument("--adjust-learning-rate",
dest="enable_lr_adjust",
action='store_true',
help="Enable learning rate adjustment")
#parser.add_argument("-m","--model-file", dest="model_path", help="The file path to load the model from")
args = parser.parse_args()
args.cwd = os.getcwd()
if args.out_dir is None:
args.out_dir = 'corelm-' + U.curr_time()
U.mkdir_p(args.out_dir)
L.quiet = args.quiet
L.set_file_path(os.path.abspath(args.out_dir) + "/log.txt")
L.info('Command: ' + ' '.join(sys.argv))
curr_version = U.curr_version()
if curr_version:
L.info("Version: " + curr_version)
if args.emb_path:
U.xassert(
args.vocab,
'When --emb-path is used, vocab file must be given too (using --vocab).'
"--vocab-file",
dest="vocab_path",
required=True,
help="The input vocabulary")
parser.add_argument("-dir",
"--directory",
dest="out_dir",
help="The output directory for log file, model, etc.")
args = parser.parse_args()
U.set_theano_device('cpu', 1)
from dlm.models.mlp import MLP
if args.out_dir is None:
args.out_dir = 'corelm_convert-' + U.curr_time()
U.mkdir_p(args.out_dir)
# Loading CoreLM model and creating classifier class
L.info("Loading CoreLM model")
classifier = MLP(model_path=args.corelm_model)
args_nn = classifier.args
params_nn = classifier.params
U.xassert(
len(params_nn) == 7,
"CoreLM model is not compatible with NPLM architecture. 2 hidden layers and an output linear layer is required."
)
embeddings = params_nn[0].get_value()
W1 = params_nn[1].get_value()
W1 = np.transpose(W1)
