-
-
Notifications
You must be signed in to change notification settings - Fork 306
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
RTDETRv2 #179
Comments
v2有哪些结构上的变化呀ovo |
Do you have smaller model which can be trained on 3080ti? |
求大佬更新pytorch v2! |
@lyuwenyu 大佬 v2年前可能开源吗 |
@lyuwenyu 大佬,来催更了。之前的预训练模型里面的 add op 有 infinity 数据。模型量化会有问题 |
我的问题我们已经解决了,在我司的芯片上运行效果挺好。 |
RTDETR可以转rknn吗? |
waiting |
您好,请问v2有投稿意向吗?能得知大概会在什么时间范围内放出嘛? |
@Peterande 非常抱歉本 另外也非常高兴社区有
如果有疑问和其他想法 欢迎继续讨论 |
非常感谢您的解答和分享!我已经明白了RTDETRv2的情况,也感谢您团队对社区的贡献和开源精神。 |
感谢感谢,现在就卡在 deformable attention,好多板子支持的不好。 |
源代码什么时候到? |
Hi |
你好,我使用 这是训练命令: export CUDA_VISIBLE_DEVICES=0,1,2,3
python -m torch.distributed.run \
--master_port=9909 \
--nproc_per_node=4 \
tools/train.py \
--config configs/rtdetrv2/rtdetrv2_r18vd_120e_coco.yml \
--use-amp \
--seed 0 这是训练记录: |
@imyhxy 可以使用最新的torch版本再试一下, 这是48.1的log |
This repo has no relevant tools. You need to find third-party tools. @babakbch |
@lyuwenyu 我使用了torch 2.4.1来训练的,我也对比了提供日志中的超参数,和我训练的基本一致的,只有collate_fn有区别,日志是CollateFuncion,仓库里的配置是BatchImageCollateFuncion。 请问你使用了的pytorch,opencv,CUDA和cudnn版本是多少。 |
这些都没有记录 日志上传的时间是在8月份时候 torch应该是用的2.4吧。 不好意思 时间有点久了 机器已经释放了。 @imyhxy |
https://arxiv.org/abs/2407.17140
I will release the rtdetrv2 soon, which will provide a better deployment experience and higher accuracy.
You can start this repo to follow news
The AP of rtdetrv2_r18vd on the COCO-val2017 dataset is increased by 1.4 and maintains the same inference speed compared with RTDETRv1. In addition, in order to make rtdetr everywhere, we provide rtdetrv2_r18vd_dsp that utilizes
discrete deformable attention
instead ofdeformable attention
with negligible differences on AP50val compared with rtdetrv2_r18vd.Figure
The text was updated successfully, but these errors were encountered: