yangp
yangp
How can I fuse the results of the orientation task and the segmentation task to enhance the final result? Thank you! Looking forward to your reply!
> 你好，请问下如果用onnxruntime-gpu的话，链接库的代码在哪里修改
I can run this code by cpu, but it reports mistakes when I choose gpu. I think my cuda is normal because I have do some regular methods to verify...
@jblindsay Hello! Do you know another algorithm used for line vectorization in addition to arcpy?
The edge label is a binary map. Is there a way to convert the edge label to oritentation label?
It means that I can convert the polygon label into the oritentation label, is that right?
``` condition = overlap[box] > max_overlap condition = torch.tensor(condition, dtype=torch.uint8).to(device) suppress = torch.max(suppress, condition) ```
@NoviceMAn-prog Hello, Have you fix this problem?
I fixed this problem by myself. Just using the code "from torchvision.datasets import VisionDataset". ------------------ 原始邮件 ------------------ 发件人: ***@***.***>; 发送时间: 2022年12月1日(星期四) 下午3:21 收件人: ***@***.***>; 抄送: ***@***.***>; ***@***.***>; 主题: Re: [lightly-ai/lightly] torchvision and...
Hello, bro! can you solve this problem?