-
/!\ PLEASE INCLUDE THE FULL STACKTRACE AND CODE SNIPPET
**Short description**
Could not load robotics datasets such as `berkeley_autolab_ur5`
**Environment information**
* Operating System: Ub…
yepw updated
7 months ago
-
Hi ,thanks for your excellent work.
Have you ever try to work on the domainNet dataset ? SInce I can't get satisfied result by changing the dataset only.
-
While running "domainbed.scripts.collect_results", I am getting the "KeyError: 'env5_in_acc" error. Also, I notice the "DomainNet experiment" just print env0-env4 while it supposed to print env5 as …
-
Dear authors,
As I understand the variable 'scores' is already a normalized probabilities, why in the softmax_kl_loss function, you used log_softmax not log directly? As I understand, the KL diverg…
-
Although highlight in the paper that "we make no extra modification for Domainnet", why are the data txts for Domainnet much smaller than original dataset?
Thanks!
-
Hello everybody, we are currently examining different DA method and tried to reproduce the SDAT paper results on our system.
So far I have made two trainings with all the settings and arguments I co…
-
We have observed an issue in our experiments involving open class + domain shift on the OfficeHome and DomainNet datasets. When using the default learning rate of 1e-05, the model tends to overfit to …
-
Dear authors, thanks for your great work.
Can you provide the image_unida_list.txt for DomainNet?
Meanwhile, is the setup for DomainNet and VisDA the same? e.g., training epochs for source and targe…
-
Hi John,
Fantastic work you have done!
I see you add an additional dataset experiment on this repo, that's the DomainNet which is not included in the paper.
May I have the Experimental Settin…
-
When I run the example code,
`corruptions = ['fog']`
`x_test, y_test = load_cifar10c(n_examples=1000, corruptions=corruptions, severity=5)`
I get the error,
` File "/projects/dali/mayanks4/TP…