Open Yshelgi opened 1 week ago
您好,感谢您将 Mamba 带到 yolo 系列方面的出色工作,但是当我在 widerface + 私人数据上训练 Mamba-yolo-T 时,结果低于 yolov8-n。
曼巴-约洛-T
约洛夫8-N
我只是换成,你有什么好的建议吗?
Detect head``Pose head
Thank you for your great interest in our work, we trained on COCO and VOC and reported it in the paper, in fact we also tried training on some downstream tasks such as CrowdHuman and CityScapes all with some relatively good results, so far nothing like what happened during your experiments. In fact, you could also try using pure Mamba in combination with YOLOv8 to explore better results in downstream tasks by further ablation experiments, but of course this is just our suggestion. However, your experiment is very valuable, which will help us to further optimize the whole Mamba architecture in the exploration of detection. In the future, we will introduce some more suitable Mamba-YOLO for downstream tasks and update it in the code base, please pay attention to it.
Hi, can you provide your cuda and torch , torchvision, torchaudio version? I have tried many diffrent version, which not success. Thanks!
Hi, can you provide your cuda and torch , torchvision, torchaudio version? I have tried many diffrent version, which not success. Thanks!
Hi, can you provide your cuda and torch , torchvision, torchaudio version? I have tried many diffrent version, which not success. Thanks!
Thanks! Moreover, can you provide the python version for me?
Hi, can you provide your cuda and torch , torchvision, torchaudio version? I have tried many diffrent version, which not success. Thanks!
Thanks! Moreover, can you provide the python version for me?
I took a look at the issue you raised. It seems that your problem has nothing to do with the python version. After all, the compilation is mainly for cu
and c++
files.
try to update gcc version
Hi, can you provide your cuda and torch , torchvision, torchaudio version? I have tried many diffrent version, which not success. Thanks!
Thanks! Moreover, can you provide the python version for me?
Hi, can you provide your cuda and torch , torchvision, torchaudio version? I have tried many diffrent version, which not success. Thanks!
Thanks! Moreover, can you provide the python version for me?
I took a look at the issue you raised. It seems that your problem has nothing to do with the python version. After all, the compilation is mainly for
cu
andc++
files.try to update gcc version
OK! Thanks! I will try it. Thanks for you!
Hello and thank you for your good job in bringing Mamba to the yolo-series,but when i train Mamba-yolo-T on widerface + private data,the results are lower than yolov8-n.
Mamba-yolo-T![image](https://github.com/HZAI-ZJNU/Mamba-YOLO/assets/50126188/5f715e02-7887-46cf-88fd-43a3b5c1fc15)
yolov8-n![image](https://github.com/HZAI-ZJNU/Mamba-YOLO/assets/50126188/14482200-7e8a-4d17-bbd3-01d503e464d5)
I just change
Detect head
toPose head
,do you have any good advice?