Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/fooSynaptic/BERT_classifer_trial
BERT trial for chinese corpus classfication
https://github.com/fooSynaptic/BERT_classifer_trial
nlp-machine-learning text-classification text-entailment
Last synced: 6 days ago
JSON representation
BERT trial for chinese corpus classfication
- Host: GitHub
- URL: https://github.com/fooSynaptic/BERT_classifer_trial
- Owner: fooSynaptic
- Created: 2018-11-30T09:41:22.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2019-03-29T03:22:21.000Z (over 5 years ago)
- Last Synced: 2024-08-02T08:09:55.892Z (3 months ago)
- Topics: nlp-machine-learning, text-classification, text-entailment
- Language: Python
- Size: 116 KB
- Stars: 7
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-bert - fooSynaptic/BERT_classifer_trial
- awesome-transformer-nlp - fooSynaptic/BERT_classifer_trial - BERT trial for Chinese corpus classfication. (Tasks / Classification)
README
# BERT_classifer_trial
BERT trial for chinese corpus classficationPlease download pretrained BERT chinise model from [Pretrained Chinese Model](https://storage.googleapis.com/bert_models/2018_11_03/chinese_L-12_H-768_A-12.zip)
Just run `launch.sh` then the fine-tune process will intial.
Please modify the path from `launch.sh` and the path of out_dir in the `run_classfier.py` script
If you want to do the inference, you need to prepare the test file and open do_predict in `run_classfier.py`.
Script `predict_eval.py` may help you evaluate the inference result.