-
Because of the fact that Japanese mixes phonetic scripts and Chinese characters, special algorithms and dictionaries are needed to run tokenizers for these these models. A popular example of this is t…
-
bert-base-serving-start \
-model_dir C:\workspace\python\BERT_Base\output\ner2 \
-bert_model_dir F:\chinese_L-12_H-768_A-12
-mode NER
如题，请问为什么需要bert_model_dir。在已经训练好model_dir 后，直接拿它预…
ghost updated
4 years ago
-
我的是do_train, do_eval, do_predict同时为true的时候的f1正常； 训练结束后想再做predict则f1为0.
我的命令行如下:
bert-base-ner-train --do_train=False --do_eval=False --do_predict=True --data_dir=data1/ --predict_batch_siz=16 --max_…
-
I am following the
[Text Classification of MultiNLI Sentences using BERT](https://nbviewer.jupyter.org/github/interpretml/interpret-text/blob/master/notebooks/text_classification/text_classification_…
-
在自己数据集上运行script/run_ner_crf.sh， 运行之后就卡在这里了，求大佬建议
Some weights of the model checkpoint at ./BERT-NER-Pytorch-master/prev_trained_model/bert-base-chinese were not used when initializing BertCrfFor…
-
Due to the huge influence of BERT, it has been reported by the Chinese media and academia. However, there is no complete Chinese translation of the paper, so I want to translate the paper and put the …
-
您好，我在执行gen_emb_Bert.py时报错如下
```
AssertionError: Could not compute output Tensor("Encoder-12-FeedForward-Norm/Identity:0", shape=(None, 512, 768), dtype=float32)
```
gen_emb_Bert.py程序文件只改了一些文件的路径，以…
-
例如：开嗯好呃
Traceback (most recent call last):
File "../vits_chinese-2.0/vits_infer.py", line 77, in
phonemes, char_embeds = tts_front.chinese_to_phonemes(item)
File "..\vits_chinese-2.0\vi…
-
run in pycharm terminal like below:
----------------------------------------------------------------------------------------------
Microsoft Windows [版本 10.0.17134.706]
(c) 2018 Microsoft Corporati…
-
环境：
PaddleHub 1.8.1
PaddlePaddle 1.8.4
paddle-gpu-serving >=0.8.2
ujson >=1.35
```
# coding: utf8
from paddlehub.serving.bert_serving import bs_client
if __name__ == "__main__":
#…