-
Hello.
With regards to your "ChemGAN"
for drug discovery, I am having a hard time istalling
the libraries....
**import model
import mol_metrics
import music_metrics
gen_dataloader import Ge…
-
请问对于 textcnn 而言，做 Binary-class text classifcation、Multi-class text classification、Multi-label text classification 这三个任务，实现区别有哪些不同？看了下代码，只看到 loss 和 evaluate 有点不一样
-
There exists a similar task that is named text classification.
But I want to find a kind of model that the inputs are keyword set. And the keyword set is not from a sentence.
For example:
```
…
-
steps to reproduce:
1. rasa train nlu \
--config ./configs/$agent/rasa_config.yml \
--nlu ./core/$agent/training_data.json \
--fixed-model-name core_$agent \
--out ./models
-…
-
I am trying to train HiLAP on my own data, but unluckly, I got negative policy loss, and …
-
想把lz的长文本分类模型，迁移到到项目的短文本分类上，lz有试过吗？
-
``` python
if args.do_eval:
dev_data_generator = processor.data_generator(batch_size=args.batch_size, phase='dev',
with_pos=with_po…
-
Research & Apply best practices/techniques to improve BERT
For starter: https://ruder.io/deep-learning-nlp-best-practices/index.html#bestpractices
Checklist:
- [x] BERT with TextCNN at the top …
-
训练时验证集的准确率为93%,但是在测试阶段,用pred_tet获得准确率只有41%,使用的是Capsule和TextCNN,10月28日左右的模型,正在排查问题
-
## ❓ Questions & Help
I want to classify products on an e-commerce site. For example, if we take Amazon for example if a product name is iPhone XS then it should be categorized to Electronics -> …