recognizer = hanlp.load(hanlp.pretrained.ner.CONLL03_NER_BERT_BASE_UNCASED_EN)
出现
Done loading 197 BERT weights from: C:\Users\Changgf\AppData\Roaming\hanlp\thirdparty\storage.googleapis.com\bert_models\2018_11_03\chinese_L-12_H-768_A-12\bert_model.ckpt into <bert.model.BertModelLayer object at 0x000001884887EC50> (prefix:bert). Count of weights not found in the checkpoint was: [0]. Count of weights with mismatched shape: [0]
Unused weights from checkpoint:
bert/pooler/dense/bias
bert/pooler/dense/kernel
cls/predictions/output_bias
cls/predictions/transform/LayerNorm/beta
cls/predictions/transform/LayerNorm/gamma
cls/predictions/transform/dense/bias
cls/predictions/transform/dense/kernel
cls/seq_relationship/output_bias
cls/seq_relationship/output_weights
这是什么意思呢？
