FewRel
FewRel copied to clipboard
thunlp
A Large-Scale Few-Shot Relation Extraction Dataset
Hi, I've downloaded the code and pretrained file as instructed in my Win10 system. My files under the path looks like: `data/ LICENSE pair-bert-train_wiki-val_wiki-5-1.pth.tar pretrain/ readme.md fewshot_re_kit/ models/ paper/ pretrain.tar...
在metanet的代码中这里传入了None ``` fewshot_re_kit.framework.FewShotREModel.__init__(self, None) ``` 但是在FewShotREModel中Dataparallel需要传入参数，否则报错 ``` class FewShotREModel(nn.Module): def __init__(self, my_sentence_encoder): ''' sentence_encoder: Sentence encoder You need to set self.cost as your own loss function. ''' nn.Module.__init__(self) self.sentence_encoder =...
Hello, I've been using OpenNRE ([https://github.com/thunlp/OpenNRE](url)) to extract sentence-level relations of texts (Supervised RE), and I would like to test Few-Shot RE for the same purpose. However, I couldn't integrate...
```python self.mask_embedding.weight.data.copy_(torch.FloatTensor([ [1, 0, 0], [0, 1, 0], [0, 0, 1], [0, 0, 0]])) ``` 这里的mask是不是应该是 ```python self.mask_embedding.weight.data.copy_(torch.FloatTensor([[0, 0, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1]])) ```
As submission upload has been disabled in the old colab competition, answer cant be uploaded for a result. Hope change the old to new colab competition soon. Thanks!
学长您好， 请问您能否将fewrel1.0 和 2.0 搬到新的CodaLab 网站 https://codalab.lisn.upsaclay.fr/. 之前的老网站 https://competitions.codalab.org/ 时不时就会出问题。 现在 https://competitions.codalab.org/competitions/27981 又没法连接了。 或者请问能否将test data 发我一份到[email protected]. 因为我在赶EMNLP的rebuttal, 现在非常需要test result 😭. 谢谢！
您好，在我使用"python train_demo.py --encoder roberta --pretrain_ckpt /model/roberta-base"命令时，运行到proto.py的37行出现了"AttributeError: 'str' object has no attribute 'size'“错误，我进行了debug，然后发现proto.py中的第34行support_emb的值是一个str类型，但是却在37行使用了.size属性，为什么会出现这种情况呢，self.sentence_encorder(support)返回的是一个字符类型吗？我该怎么处理呢，谢谢
你好， 我把四个 pred-$N-$K.json 文件压缩到一个.zip 文件上传后得到这个错误： WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap. Traceback (most recent call last): File...
python train_demo.py \ --val val_wiki \ --model snail \ --encoder cnn \ --trainN 10 \ --N 5 \ --K 1 \ --val_step 1000 模型报错如下： ../aten/src/ATen/native/cuda/Indexing.cu:1141: indexSelectLargeIndex: block: [18,0,0], thread: [123,0,0]...
