CocoZou1994
CocoZou1994
Yeah, right! 在 2022-09-27 10:22:25,"Xiuxiu21" ***@***.***> 写道: Thanks for your attention! line 268 is ok. line 127 is modified 这里是否也需要修改呢 — Reply to this email directly, view it on GitHub,...
you should check the input data, detail about the Lines 213-248 "sample = transform(sample)"
Yeah, it's right. It may be a problem with the torch version, cdist() calculates dim=2 by default, and then the omega initialization is (1, out, int, 1, 1). It will...
This may be a problem with your gt and dice loss function settings? Can you provide more details?
Yeah, it may be solved. What's your question about the focusnetv2?
I have used his source code to my own task, but did not follow up his source code to reproduce his results. I pay more attention to the heatmap in...