moyan007

evaluate demo for the corresponding indicators MOTA MOTP and so on

7

Hello sir, Thanks for your sharing firstly. I met a trouble when I evaluate the system(your demo and modified version). Only got the wrong results like follows: ********************* Your MOT16...

您好请问关于DPE模型的实现您这边有做一些相关的工作可以分享的么

1

最近研究DPE模型框架，但是一直没想好如何实现验证，不知道您这边是否有资源分享，感谢

感谢分享。我想咨询下如何如何把两个NER模型融合的给拆开，比如我只要bert的NER模型然后接一个ELmodel进行pipeline处理，不采用融合的方式。之前改了一版，没处理太对，想咨询下需要特别处理某些地方吗，能否麻烦给点建议！

How can I do to make the code suitable for pytorch 0.4+? Anyone can give me some advices? Thank you a lot.

As the title, please！

As the title please.

I trained the demo on the cityperson dataset, but only got a pretty low result, about 0.2 +. Could any one please help me with that?

RuntimeError: expected a non-empty list of Tensors

2

I met a trouble that 'RuntimeError: expected a non-empty list of Tensors'. Could anyone please help me with that? Traceback (most recent call last): File "/home/Downloads/school/Repulsion_Loss/train.py", line 182, in main()...

tensorflow.python.framework.errors_impl.InternalError: cudaGetDevice() failed. Status: CUDA driver version is insufficient for CUDA runtime version

1

Hello, Mr.liu! I am learning about your paper and test the project you uploaded. However, I got the error that "tensorflow.python.framework.errors_impl.InternalError: cudaGetDevice() failed. Status: CUDA driver version is insufficient for...

请问，用于做词频统计的new_corpus是怎么来的呢？

1

如题，感谢分享！