liujiachang
liujiachang
thanks, because I can run this data in ufldv1, so I don't deal with data for ufldv2.
I'm trying to migrate to my own data (intersection surveillance video). Maybe the effect is not ideal due to different angles. Do you have any good suggestions? I can make...
I tried to enhance the data, and it did work, but the effect still couldn't meet the requirements. Now I'm trying to turn the picture into a bird's-eye view. Maybe...
I also encountered this issue, but it can run normally on Jetson 5.1.2.
I think it's a problem with the installation of ffmpeg. OpenSSL was not enabled during the installation of ffmpeg. I added '-- enable openssl \' after each method in the...
文档中没有搜索到request.post的方法,有curl和openai的样例。而且我用openai的方式进行请求,流式输出仍然是卡顿的,和request的时候一致,一段一段输出。是否是有某些参数导致存在缓存。
测试出来了,不是代码问题,是部署的平台还有一层代理转发机制,此问题可关闭。
是否有方法可以修改流模式的分隔符,比如将\n改为\r\n。
仍然报错,报错的内容与 #1951 相同
> @liujiachang 同样报错,请问解决了吗 已解决,但我不确定这对你是否有效,我重新搭建了环境,降低了torch的版本,现在我的torch版本为:torch-npu 2.3.1