Chief Accelerator

How long does it take to receive the dataset email?

6

3 days has passed.

Cannot train pytorch version on multi-gpu

1

When trained on multi-gpu, the transfer loss (CDAN + Entropy loss) is very low and the test accuracy alway decreases. Dataset: visda2017 tested on Ubuntu 18.04, Pytorch version: 1.2.0 /...

Cannot reproduce the results on office31 and visda (vanilla)

2

Hi, the paper says you have used 10-crop during evaluation. But it didn't appear in the code. In addition, I cannot reproduce the results on both office31 and visda: 1)...

The download link is broken

10

The link https://drive.google.com/drive/folders/0B-aa7y5Ox4eZWE8yMkRkNkU4Tk0 is broken, as well as the download script. Could you please update the link? Thanks.

Numerical Misalignment between nyu_class and color_ply

3

Thanks for your work. I am trying to preprocess data like what you did in CVPR'18 (Pointwise Conv), but with different block sizes, strides. etc. However, there seem to be...

Code for medical dataset

3

Could you please release the code for medical datasets? Thanks!