Ma Jimmy
Ma Jimmy
问题已经解决，请看 https://github.com/open-mmlab/playground/pull/164 获取Outlook for Android ________________________________ From: Hebei Li ***@***.***> Sent: Sunday, October 15, 2023 2:58:33 PM To: open-mmlab/playground ***@***.***> Cc: Ma Zhiming ***@***.***>; Comment ***@***.***> Subject: Re: [open-mmlab/playground] 如何使用label_anything只做分割标注？根据教程标注出来的是目标检测加分割？...
是否使用的anaconda cmd？
Are the endpoints of your back-end reasoning not reserved? This will cause you to be unable to use back-end reasoning on the front-end.
> > 你的后端推理的端点没有保留吗？这会导致你无法在前端使用后端推理。 > > hello, how did you solve this problem? Make sure that both the front-end of label studio and the machine learning inference back-end are present at...
> > > > 你的后端推理的端点没有保留吗？这会导致你无法在前端使用后端推理。 > > > > > > > > > 您好，您是如何解决这个问题的？ > > > > > > 确保标签工作室的前端和机器学习推理后端同时存在，这意味着您需要打开两个终端，而不是使用 ctrl + c 取消其中一个程序 > > I have...
This error looks like it happens when the LS backend reads based on the image url, ask if the backend inference and the dataset are in the same device.
Is the anaconda powershell prompt being used?
你好，转换脚本是针对label studio导出的rle格式转换为COCO格式，如果需要导出polygon的话可以直接使用LS导出COCO格式。
It looks like it's caused by you not downloading the weights to the corresponding paths.