Lishijie
Lishijie
### Is your feature request related to a problem? Please describe. RuntimeError: CUDA error: an illegal memory access was encountered CUDA kernel errors might be asynchronously reported at some other...
拜读了下您的code,对于评价指标,我有一些疑问,对于rank1、rank5、rank10,它们的计算不都是按照匹配的正确的多少计算的吗?而在您的code中,区分了good_index和junk_index,其中junk_index中包括了同摄像头下的同一个人的index,这样做会使得,rank1等的值变小,目的是增强鲁棒性吗?在一般认可的评价行人重识别指标时,都是这么做的吗?十分期待您的回复。
这个模型怎么改成ddp训练的方式呢?这样可以将batchsize调高,会不会提高rank1呢?对于提高rank1,您有什么建议吗,我都试过了,PCB的rank1才达到93%多,map才84%,期待作者的回复~ 顺便说一下,因为test.py更改了,之前的模型的配置文件缺少信息,需要添加信息,否则无法运行,
新手村新手,环境问题
目前在ubuntu下,有gradle环境和openjdk version "16.0.1" 但是第一步编译就把我拦下来了, 编译: gradlew jar 出错: Command 'gradlew' not found, did you mean: command 'gradle' from deb gradle (4.4.1-13) Try: apt install 我就用 ./gradlew jar 然后就 Starting a...
When installing dependencies, the minimum version of pyembree is 0.1.8, the minimum requirement for python is 3.8, and the installation of python3.6 in element.yaml, and the installation of pyembree is...
Hello, can you access the fine-tuned model with this repository after running it? Or can you access an API for your own trained model? I'm not very familiar with this...
if we use python==3.9.13, sklearn is not used. so we should modify sklearn to scikit-learn in requirements.txt
https://huggingface.co/THUDM/agentlm-7b , I try it,but far below 84% in alfworld-std. Is it the wrong model?
https://cs-people.bu.edu/dasabir/raid.php, this url is not exist. can you provide a new link for download?