Haotian Chen

checkpoint: segformer.b5.1024x1024.city.160k.pth CS-val: +--------+-------+-------+-------+ | Scope | mIoU | mAcc | aAcc | +--------+-------+-------+-------+ | global | 82.39 | 89.24 | 96.73 | +--------+-------+-------+-------+ CS-test: +--------+------+------+------+ | Scope | mIoU...

Could you share the sentimenthx.npy？

Gu老师你好！我是一个研二的学生，同样是做的DA. 看了你的RSDA工作，深有启发。想请教你，在运行CDAN_VisDA-2017的时候（使用原始RGB图片作为输入），我无论使用resnet50，还是resnet18或resnet101作为backbone，结果都只有不到40，我看你们都是70+的acc. 方便分享一下你的code，或者大概指点一下吗？其他baseline效果都不高。 期待Gu老师的答复，感激不尽！

I have a question regarding the computation of cosine similarity between task vectors. Should the cosine similarity be computed by flattening all parameters into a single vector (high memory cost),...