-
#### Issue Description
As I described in https://github.com/deeplearning4j/deeplearning4j/issues/4513 I created the Char CNN - BiLSTM https://gist.github.com/aleksei-ai/7200e80634611a3adbb8efaaed616…
-
#### Issue Description
Can't implement a parallel network of CNN and LSTM because I can't merge the outputs from both networks.
I am using the IMDB database, and calling the dataset iterators l…
-
我在使用框架完成中文NER任务时，数据是用BIO格式标注的，训练一切正常，但是decode的时候生成的文件有部分数据会丢失。比如一个5219行的文件，decode之后只剩下前3429行。一个50W行的文件decode之后的文件只有30多W行，decode过程没有任何报错信息，请问有可能是什么原因造成的？是数据的问题吗？感谢您
下面是train的config文件
### I/O ###
t…
-
本体和知识图谱学习
https://blog.csdn.net/Solitarily/article/details/78768139
-
mldl@mldlUB1604:~/ub16_prj/BiLstm_CNN_CRF_CWS$ python3 embedding_model.py
Using TensorFlow backend.
Traceback (most recent call last):
File "embedding_model.py", line 20, in
sentences=MySen…
-
https://github.com/UKPLab/emnlp2017-bilstm-cnn-crf/blob/master/util/CoNLL.py#L81
```
if newVal[0] == 'B':
if oldVal != 'I'+newVal[1:]:
newVal = 'I'+newVal[1:]
```
Are these codes right…
-
Hi,
I tried running the Train_Chunking.py on a GPU namely a 1080Ti and a Tesla V100 AMI by changing the elmo_cuda_device = 0 on Line 52. It seems to run out of memory on both the 1080Ti and the V10…
-
Hello,
I'm trying to use ELMo for longer document (average about 600-900 words), and my batch size is 32. I'm using ELMo jointly with a uni-directional LSTM on top, and I'm using GTX 1080-Ti.
`…
-
Hi,
I'm unable to reproduce results for ConLL2003 NER data.
I even tried converting my data from BIO-BIOES using your script. Please help me understand what I've done wrong.
Below is the log with…
-
我使用LatticeLSTM项目中您提供的ResumeNER数据集，训练了多次，结果都是不收敛，请问可能是什么问题？多谢您啊！以下是我的日志记录：
```
Seed num: 42
MODEL: train
Load pretrained char embedding, norm: False, dir: ResumeNER/gigaword_chn.all.a2b.uni.ite50.v…