-
Thanks for ur excellent work!
I have some questions about the dataset Visda-2017. From ur "README.md", the visda2017 is only two parts which is exactly train and validation. So ur results on this dat…
-
Would it be possible to adapt this for use in stand-alone and domain (clustering) modes?
-
Hi,
I am interested in building a DG code using MFEM at its core, specifically targeting conformal Tetrahedron adaption. Ideally this would be dynamic where the mesh would be refined or coarsened i…
-
-
Many thanks to the contributors for open-source the project, which I was very interested in, providing a solid torch experiment flow.
The following error is reported in this example as to what is t…
-
Thanks for your wonderful works and codes!
I just wonder if you use the total 200 training pairs on KITTI 2015 for domain adaption, or split the 200 pairs into a training set and a validating set as …
-
由于代码运行过程中，confu.backward()的时候会报错梯度被修改的错误，所以我稍微修改了训练流程，主要是在loss.backward()之后重新将数据放入了model然后重新计算confu的loss，但是acc unknow的值是一直在往下降。
` loss.backward(retain_graph=True)
optimizer.step()
…
-
Can you release the pre-trained model for meta-learning? It will be helpful to test online adaption on the target domain.
-
Hi Lee, recently I want to reproduce your experiments about domain adaption in this paper. But I can't find the details in your README. Could you provide some guidance? I will really appreciate that.
-
At first, Thank you for this excellent services.
I want to cartoonized 3D view from seed image. so please tell me how to adapt cartoonized image.
And second, I think, seeds in your code means ge…