import cPickle as pickle
logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)
from trans_model import Translate
# Get the arguments
if __name__ == "__main__":
config = getattr(configurations, 'get_config_cs2en')()
source = T.lmatrix('source')
target = T.lmatrix('target')
source_mask = T.matrix('source_mask')
target_mask = T.matrix('target_mask')
trans = Translate(**config)
trans.apply(source.T, source_mask.T, target.T, target_mask.T)
cost = trans.cost
#trans.load(config['saveto']+'/params.npz')
params = trans.params
for value in params:
logger.info(' {:15}: {}'.format(value.get_value().shape, value.name))
grade = T.grad(cost, params)
# add step clipping
if config['step_clipping'] > 0.:
grad = step_clipping(params, grade, config['step_clipping'])
ltopk_trg_vocab_idx = []
if config['use_mv']:
# no need to use the whole vocabulary
v_part = T.vector('batch_target_vocab', dtype='int64')
v_true = T.matrix('v_true', dtype='int64')
from manvocab import topk_target_vcab_list
ltopk_trg_vocab_idx = topk_target_vcab_list(**config)
log('{}'.format(ltopk_trg_vocab_idx))
log('{}'.format([tv_i2w[i] for i in ltopk_trg_vocab_idx]))
one_model = config['one_model']
log('Build lookup table, bi-directional encoder and decoder ... ', nl=False)
trans = Translate(**config)
# transpose all the input matrix into shape (sent_len * batch_size)
if config['use_mv']:
trans.apply(source.T, source_mask.T, target.T,
target_mask.T, v_part, v_true)
else:
trans.apply(source.T, source_mask.T, target.T, target_mask.T)
log('Done\n')
if config['reload']:
log('Reload model {}'.format(config['one_model']))
trans.load(one_model)
# actually the average cross entropy (cost) per sentence in a batch
cost = trans.mean_cost
log_norm = trans.mean_abs_log_norm
import logging
import configurations
from sample import multi_process_sample, gen_sample
import cPickle as pickle
logger = logging.getLogger(__name__)
from trans_model import Translate
# Get the arguments
import sys
if __name__ == "__main__":
config = getattr(configurations, "get_config_cs2en")()
trans = Translate(**config)
params = trans.params
print params[0].get_value().sum()
logger.info("begin to build sample model : f_init, f_next")
f_init, f_next = trans.build_sample()
logger.info("end build sample model : f_init, f_next")
src_vocab = pickle.load(open(config["src_vocab"]))
trg_vocab = pickle.load(open(config["trg_vocab"]))
src_vocab = ensure_special_tokens(
src_vocab, bos_idx=0, eos_idx=config["src_vocab_size"] - 1, unk_idx=config["unk_id"]
)
trg_vocab = ensure_special_tokens(
trg_vocab, bos_idx=0, eos_idx=config["src_vocab_size"] - 1, unk_idx=config["unk_id"]
)
args.watch_adist, args.merge_way, args.ifapprox_dist, args.ifapprox_att,
args.add_lmscore, args.ifsplit]
valid_set = args.valid_set
kl = args.m_threshold
nprocess = args.n_process
lmpath = args.lm_path if args.lm_path is not None else None
ngram = args.ngram
alpha = args.length_norm
beta = args.cover_penalty
dec_conf(switchs, beam_size, search_mode, kl, nprocess, lmpath, ngram, alpha, beta, valid_set)
config = getattr(configurations, 'get_config_cs2en')()
_log('init decoder ... ')
trans = Translate(**config)
_log('done')
_log('build decode funcs: f_init f_nh f_na f_ns f_mo f_ws f_ps f_ce f_next f_emb ... ', nl=False)
fs = trans.build_sample()
_log('done')
y_im1 = [2]
npy = np.asarray(y_im1)
if npy.ndim == 1:
x = npy[None, :]
# context = np.random.sample((7, 1, 2048)).astype(np.float32)
# s_im1 = np.random.sample((1, 1024)).astype(np.float32)
debug('............. time testing ..............................')
s = time.time()
s_im1, ctx, c_x = fs[0](x)