Noé
Noé
The new version of Pytorch does not support module names with a "." in their name. You can either use an older version, or patch the `state_dict` file, as well...
Also see issue #4
see issue #47
You need to write your own data loader like in the loader module. I recommend going through the code with a known dataset and trying to understand what it does....
It might be because you have a pytest installed and it assumes test.py is a test file and run it as such. Try renaming test.py to another name (e.g. demo.py)...
Not exactly sure what is causing the error, but it will disappear if you turn data augmentation off
@Deso2121 @a-bakhtiari Did you find a fix?
> > I will see about creating an example for combinging with painlessmesh and espmesh or espnow > > > > * [ ] example candidate > > @tablatronix -...
I wonder the same thing. It does seem that the same annotation format holds for the 2020(named 2019) dataset
Yes, @sidoh , having the same issue when deploying the lambda within a VPC.