-
python3 train.py -c configs/rec/rec_icdar15_train.yml 2>&1 | tee train_rec.log
2020-11-25 15:08:02,934-INFO: {'Global': {'debug': False, 'algorithm': 'CRNN', 'use_gpu': False, 'epoch_num': 1000, 'log…
-
Hi, I'm new to AllenNLP. I was trying to simply run scicite to predict the provided `test.jsonl` file using the pre-trained `scicite.tar.gz`, but got the following error. Can you please help me fixing…
-
If yes,How long will you take add predict.py for OPE and OTE tasks?
-
While working on text recognition inference, we observed a huge drop in accuracy of inference model while that for pre-trained model was comparatively better.
We noticed our text recognition pretrai…
-
我想直接使用预训练模型参数试一下结果，可是报了个keyerror，这是为啥
from kashgari.tasks.labeling import BiLSTM_Model
from kashgari.embeddings import BertEmbedding
from kashgari.corpus import ChineseDailyNerCorpus
train_x, tr…
-
你好，请问您用的什么方法替换wordpiece处理输入呢
-
Hi @dsindex
I'm getting the following error, while running `evaluate.py` with these parameters:
`evaluate.py --config=configs/config-bert.json --data_dir=data/conll2003 --model_path=pytorch-mod…
geo47 updated
3 years ago
-
如题，根据给出的rec_mv3_none_bilstm_ctc.tar预训练模型，icdar2015数据集和label，i在修改yml之后使用了预训练模型，训练300个epoch后收敛，最佳为第102epoch，但第102和300模型识别icdar训练集图像错误率约90%以上，更别提测试集了，显存不足batchsize目前改为32，由于新入门不确定参数是否有错，希望各位不吝赐教
basical…
-
ubuntu 18.04
python 3.6.12
tensorflow 2.3.0
First, thanks for your efforts on code2vec, code2seq and etc. I am very interested in this work, and try to learn the code details.
Followed your …
-
@eftekhar-hossain @omar-sharif03
In your paper, it is mentioned that these classifiers are used for task A
CNN + BiLSTM
SVM + TF-idf
SVM + Word2Vec (ED=200)
SVM + Word2Vec (ED=150)
In th…