18022443868
18022443868
the same question
> @ 18022443868 本文不清楚图5(c)中Ge模块分支的通道号。 128?
> @ 18022443868 本文不清楚图5(c)中Ge模块分支的通道号。 You're right, wait for the original author to open source
Bisenetv2 available in embedded real time?
Ok, thanks for your solution, open source and test again > @ 18022443868我认为很难。另外,我的训练速度比V1慢,我不知道为什么吗? Ok, thanks for your solution, open source and test again
> 我会尝试的。阅读完本文后,有些细节我不太清楚,因此复制起来可能并不容易。我会更新,如果我能达到的准确性。 Thank god for coming back. Sit back!!!
有人在Pycharm上面运行成功的吗?有使用教程?跪求跑通的给一份参考指南啊。
> 您好sounansu,非常感谢您的反馈和报告。如果您有兴趣,也可以尝试使用较小的批次大小和较高的分辨率。另外,我建议使用较小的批处理大小保留v_loader的完整分辨率,以使图像在验证期间不会失真。谢谢! Could you please tell me the configuration version of scipy package for training?In a Linux environment?How about under Windows?
> 1024,2048 Please check out your version of Windows pytorch and other package versions
The above CUDA errors occur in training