-
I'm getting this issue when I run training on a08 entity network and a06 seq2seq models.
Can I get or train this file?
zhihu-word2vec-title-desc.bin-100
![screenshot_20170720_171417](https:…
-
1. TextCNN rand model downloads pretrained word vectors even if not needed. rand model initializes word vectors randomly and updates in the training process. So, I think there is not need to download …
-
在测试的时候,不需要dropout吧?
-
Thank you for making this code open and available to the community. It is easy to use. My issue is that I do not obtain the same results that you present in Table 4 of your paper.
When I train the …
-
大佬,作为一个新人,对于代码的理解力还不是么强!所以相结合博客来学习一下!比如:项目中的BERT+CNN进行训练,那么此处的CNN是不是TextCNN那一套?BERT最终训练出来的是字向量还是句子向量?而且模型的整体输入流输出流是什么!还希望能帮忙解答一下谢谢
-
Hi~Thanks very much for your work. I wonder if this method also suites for other model(such as textCNN, LSTM etc.). Thanks!
-
-
将配置文件中device属性改成了"cpu"后,运行命令:
`python train.py conf/train.json`
仍然报错:
>Use dataset to generate dict.
Size of doc_label dict is 3
Size of doc_token dict is 2629
Size of doc_char dict is 262…
-
HI!
I am trying to use the `predict_on_batch` function inside the TextCNNModel to predict the solubility for new smiles; however, I get a `TypeError: object of type 'int' has no len()`. I have copied…
-
I have run train.py with this config and after 13 epoch I still get 0 fscore.
**Config:**
```
{
"task_info":{
"label_type": "multi_label",
"hierarchical": true,
"hierar_taxonomy…