MCPcopy Create free account
hub / github.com/Lancelot39/KGSF / forward

Method forward

model.py:328–445  ·  view source on GitHub ↗

Get output predictions from the model. :param xs: input to the encoder :type xs: LongTensor[bsz, seqlen] :param ys: Expected output from the decoder. Used for teacher forcing to calculate loss. :type

(self, xs, ys, mask_ys, concept_mask, db_mask, seed_sets, labels, con_label, db_label, entity_vector, rec, test=True, cand_params=None, prev_enc=None, maxlen=None,
                bsz=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 4

infomax_lossMethod · 0.95
decode_forcedMethod · 0.95
compute_lossMethod · 0.95
decode_greedyMethod · 0.95

Tested by

no test coverage detected