lkdci

Hi @mmaaz60, thanks for the fast reply. So basically the backbone remains the same, and an ASPP module is used as Decoder?

Added changes according to the review, see implementations of factories @ofrimasad

@ofrimasad , Addressed. Init the context module through a Yaml base factory instead of dynamically initiate w.r.t to the backbone.

Added default argument to support default behavior of the RepVGGBlock, for backward compatibility. See [4972b18](https://github.com/Deci-AI/super-gradients/pull/401/commits/4972b18f1e4c037ac830b1b4cee1bdb785584a12)

@davidtvs thanks for reporting this bug, great catch! Thanks for setting up the unit test for this use case, one thing I would comment on, is instead of checking whether...

This issue is fixed in master branch and will be available in the next version release. https://github.com/Deci-AI/super-gradients/pull/982 Thanks again @davidtvs for reporting the issue.

@BloodAxe Added unit tests with yolox output and mock model outputs. I will appreciate your re-review

@BloodAxe @shaydeci , conflicts resolved. As mentioned above review was addressed, I'll appreciate your re-review of the fixes

Hi @Louis-Dupont there is a design conflict about the Dataloader creation. A dataloader - dataset creation strategy can be done in two different way, ### First Approach - dataloader factory:...

Hi @MaxEAB , first thing to make sure is to use TensorRT framework fo fair comparison with the paper result. When benchamarking with `trtexec` tool there are two common conventions...