Subhankar Roy

Hi @xvjiarui thanks for sharing the class wise accuracy and IoU scores. Can you please tell me which checkpoint are you using for computing the validation scores on VOC? I...

> Running demo.py, get 'rbd' error in saliency.py: > > File "saliency.py", line 62, in > edges = [[vertices[x%num_vertices], > vertices[x/num_vertices]] for x in edges] > IndexError: only integers, slices...

Hi, if I understand correctly you want to run this code on GPUs id 2 right? Instead of out = torch.cuda(2), can you please use CUDA_VISIBLE_DEVICES=2 and leave the code...

> hi roysubhankar! @roysubhankar > there have some problems,can you help me to answer? > Traceback (most recent call last): > File "resnet50_dwt_mec_officehome.py", line 603, in > main() > File...

Hi, I will try to upload the code for MNIST->USPS by this weekend.

Hi @vcoyette , I have uploaded the code for usps mnist. This implementation contains DWT with Entropy loss. But you can easily replace the entropy loss with the MEC loss...

Hi, In our paper we actually report the cifar9->stl9 setting. If you run cifar9 as source and stl9 as target then you will see improvement over shot with our usfan...

> Thanks for your reply !!! > > Following your work, I did get the improvement over shot with usfan method from 66.0% to 68,.5%. > But I found the...

> I see the henssian file generated at the source model training is not updated during target adaptaion training step. Should the hessian file be updated when train on target...