def __init__(self, conf: ZDecoderUDEPConf, name: str, vocab_udep: SimpleVocab, ref_enc: ZEncoder, **kwargs):
super().__init__(conf, name, **kwargs)
conf: ZDecoderUDEPConf = self.conf
self.vocab_udep = vocab_udep
_enc_dim, _head_dim = ref_enc.get_enc_dim(), ref_enc.get_head_dim()
# --
self.helper = ZDecoderUDEPHelper(conf, self.vocab_udep)
self._label_idx_root = vocab_udep.get("root") # get root's index for decoding
# --
# nodes
self.depth_node: IdecNode = conf.depth_conf.make_node(_isize=_enc_dim, _nhead=_head_dim, _csize=1)
self.udep_node: IdecNode = conf.udep_conf.make_node(_isize=_enc_dim, _nhead=_head_dim, _csize=len(vocab_udep))
def __init__(self, cons: Constrainer, src_vocab: SimpleVocab, trg_vocab: SimpleVocab, conf: ConstrainerNodeConf, **kwargs):
super().__init__(conf, **kwargs)
conf: ConstrainerNodeConf = self.conf
# --
# input vocab
if src_vocab is None: # make our own src_vocab
cons_keys = sorted(cons.cmap.keys()) # simply get all the keys
src_vocab = SimpleVocab.build_by_static(cons_keys, pre_list=["non"], post_list=None) # non==0!
# output vocab
assert trg_vocab is not None
out_size = len(trg_vocab) # output size is len(trg_vocab)
trg_is_seq_vocab = isinstance(trg_vocab, SeqVocab)
_trg_get_f = (lambda x: trg_vocab.get_range_by_basename(x)) if trg_is_seq_vocab else (lambda x: trg_vocab.get(x))
# set it up
_vec = np.full((len(src_vocab), out_size), 0., dtype=np.float32)
assert src_vocab.non == 0
_vec[0] = 1. # by default: src-non is all valid!
_vec[:,0] = 1. # by default: trg-non is all valid!
# --
stat = {"k_skip": 0, "k_hit": 0, "v_skip": 0, "v_hit": 1}
for k, v in cons.cmap.items():
idx_k = src_vocab.get(k)
if idx_k is None:
stat["k_skip"] += 1
continue # skip no_hit!
stat["k_hit"] += 1
for k2 in v.keys():
idx_k2 = _trg_get_f(k2)
if idx_k2 is None:
stat["v_skip"] += 1
continue
stat["v_hit"] += 1
if trg_is_seq_vocab:
_vec[idx_k, idx_k2[0]:idx_k2[1]] = 1. # hit range
else:
_vec[idx_k, idx_k2] = 1. # hit!!
zlog(f"Setup ConstrainerNode ok: vec={_vec.shape}, stat={stat}")
# --
self.cons = cons
self.src_vocab = src_vocab
self.trg_vocab = trg_vocab
self.vec = BK.input_real(_vec)