parser.add_argument('--vocab',
help='Vocabulary file (only needed if numpy'
'embedding file is given)')
parser.add_argument('-a',
help='Plot attention values graph',
dest='attention',
action='store_true')
parser.add_argument('-i',
help='Run inference classifier',
dest='inference',
action='store_true')
args = parser.parse_args()
utils.config_logger(verbose=False)
logger = utils.get_logger()
params = ioutils.load_params(args.load)
if args.inference:
label_dict = ioutils.load_label_dict(args.load)
number_to_label = {v: k for (k, v) in label_dict.items()}
logger.info('Reading model')
sess = tf.InteractiveSession()
model_class = utils.get_model_class(params)
model = model_class.load(args.load, sess)
word_dict, embeddings = ioutils.load_embeddings(args.embeddings,
args.vocab,
generate=False,
load_extra_from=args.load,
normalize=True)
model.initialize_embeddings(sess, embeddings)
help='JSONL or TSV file with data to evaluate on')
parser.add_argument('embeddings', help='Numpy embeddings file')
parser.add_argument('--vocabulary',
help='Text file with embeddings vocabulary')
parser.add_argument('-v',
help='Verbose',
action='store_true',
dest='verbose')
parser.add_argument('-e',
help='Print pairs and labels that got a wrong answer',
action='store_true',
dest='errors')
args = parser.parse_args()
utils.config_logger(verbose=args.verbose)
params = ioutils.load_params(args.model)
sess = tf.InteractiveSession()
model_class = utils.get_model_class(params)
model = model_class.load(args.model, sess)
word_dict, embeddings = ioutils.load_embeddings(args.embeddings,
args.vocabulary,
generate=False,
load_extra_from=args.model,
normalize=True)
model.initialize_embeddings(sess, embeddings)
label_dict = ioutils.load_label_dict(args.model)
print('Label dict[Y] : ', label_dict['Y'])
# pairs = ioutils.read_corpus(args.dataset, params['lowercase'],
# params['language'])
#dataset = utils.create_dataset(pairs, word_dict, label_dict)
# whether to generate embeddings for unknown, padding, null
is_really_cont = args.warm != None or (args.cont and os.path.exists(
os.path.join(args.save, "model.meta")))
warmup_model = args.warm
if is_really_cont:
logger.info('Found a model. Fine-tuning...')
word_dict, embeddings = ioutils.load_embeddings(
args.embeddings,
args.vocab,
generate=False,
normalize=True,
load_extra_from=warmup_model)
params = ioutils.load_params(warmup_model)
else:
word_dict, embeddings = ioutils.load_embeddings(args.embeddings,
args.vocab,
generate=True,
normalize=True)
ioutils.write_params(args.save,
lowercase=args.lower,
language=args.lang,
model=args.model)
ioutils.write_extra_embeddings(embeddings, args.save)
logger.info('Converting words to indices')
# find out which labels are there in the data
# (more flexible to different datasets)