leilai li comments

Results 23 comments of


                                            leilai li

some question about DKRL

than > Hi, I reimplement the DKRL using TF. The code is at https://github.com/bxshi/ConMask/blob/master/ndkgc/models/cnn_model.py Thansk for your reply~~~ Does the code of model is cnn_model.py, not the dkrl.py? Could you...

some question about DKRL

解决问题的方法在一个关掉issue里面有提到 https://github.com/bxshi/ConMask/issues/3 ------------------ Original ------------------ From: "LeSamouraiXWH"; Date: Mon, Mar 18, 2019 09:38 PM To: "bxshi/ConMask"; Cc: "leilai li"; "Mention"; Subject: Re: [bxshi/ConMask] some question about DKRL (#6) @lileilai 您好，请问在用命令cmake...

onnxruntime/capi/onnxruntime_inference_collection.py", line 370, in _create_inference_session sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model) onnxruntime.capi.onnxruntime_pybind11_state.InvalidProtobuf: [ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from onnx_data/cpm_large_opt.onnx failed:Protobuf parsing failed.

I also meet some problem, is there a solution, thanks ~

找不到 gpt.pb.h 文件

> 运行 local_demo_gptlm demo 报错找不到 gpt.pb.h 文件 > > 谢谢请问您解决这个问题了吗？我是在编译的时候报错说找不到这个头文件 ![image](https://user-images.githubusercontent.com/25097411/192680020-6c471d8c-8518-47a8-b8c5-b5700590b26d.png)

关于分类准确率

请问有解决这个问题吗，我也碰到了这个问题，分类的准确率很低

多gpu lora 报错

请问解决了吗？+1

关于数据集和代码的一些问题

师兄 /师姐，你好～目前在follow您发表在ijcai上关于社会关系抽取的这篇文章，打算作为毕业论文，有一个问题，希望能得到您的帮助 PIPA数据集中没有原图的person-pair的两个box坐标，只是给了single_body的图片。 ------------------------- 在您给的测试集中的数据 72157624551655535_4870147689.jpg 375 333 749 767 863 183 1023 548 8 -------------------------- 请问您能提供下PIPA中peroson-pair (body)的两个box坐标的这个数据集(train/val)吗？谢谢～～～ ------------------ Original ------------------ From: "wzhouxiff"; Date: Tue, Jan 8,...