tf_ner

tf_ner copied to clipboard

Support for TF 2.0

6

Hi, Are there any plan to upgrade the library to support TF 2.0? I feel some of the new features can help simplify the code library and may also improve...

SivamPillai

There are issues when I use my own datasets

1

Excuse me, when I use my own datasets(I change the original data to my own data, and the path remains the same), there are some bugs in Pycharm, look at...

mzisbest

RuntimeError: There was no new checkpoint after the training. Eval status: missing checkpoint

2

While running this model on the CONLL2003 data ( TF 1.11) , i am getting this error global_step/sec: 3.00248 loss = 5.6152534, step = 101 (33.300 sec) global_step/sec: 2.88663 loss...

harirajeev

Hi, I have applied a customized dataset in the few shot setting, the training contains 500, valid contains 1k, and the test contains 10k examples, Then, the result on F1,...

wentinghome

In reported result, what is difference between best and abs. best ? Also mean + std. deviation doesnt matches with the best result reported in the github page ?

1

First of all, i thank you very much for sharing your code written beautifully and explained very well in your blog. I faced a problem while reading the result. 2...

a1nkit

Label probabilities for the CRF layer

4

Hi, Thanks for sharing this great implementation. I know it is possible to get the label probabilities using forward backward algorithm in CRFs. I am finding some difficulties in implementing/modifying...

ashim95

Hey, First off, thanks for your amazing implementation of Custom NER. I have been using it for my project. I am facing this issue where sometimes the data gets tagged...

shivomthakkar

Dear author: Thanks a lot for your work.Beautiful code and wonderful f1-score. I am Chinese and I need to train a Chinese NER recently(but not with BERT). I also tried...

happy-nlp

Which version of numpy will work

1

dongyang12138

has no attribute 'stop_if_no_increase_hook' for tensorflow 1.9

1

Traceback (most recent call last): File "main.py", line 171, in hook = tf.contrib.estimator.stop_if_no_increase_hook( AttributeError: module 'tensorflow.contrib.estimator' has no attribute 'stop_if_no_increase_hook'

kbwzy