In initialize only calculate current vectors hash if needed

This commit is contained in:
Adriane Boyd 2023-05-08 09:38:37 +02:00
parent dbc71ecd44
commit 8824a12c5e

View File

@ -133,6 +133,7 @@ def init_vocab(
logger.info("Added vectors: %s", vectors)
# warn if source model vectors are not identical
sourced_vectors_hashes = nlp.meta.pop("_sourced_vectors_hashes", {})
if len(sourced_vectors_hashes) > 0:
vectors_hash = hash(nlp.vocab.vectors.to_bytes(exclude=["strings"]))
for sourced_component, sourced_vectors_hash in sourced_vectors_hashes.items():
if vectors_hash != sourced_vectors_hash: