Closed mosheliv closed 4 years ago
This should probably be addressed by #923
true, but #923 does not address the user level integration. It still assumes everything will be dropped into the codebase. This is not the right approach for this, I think.
Thanks for your suggestions! The perspective is that mmdetection can act as a framework and users can develop their own methods using the components and apis without touching the codebase. With the registry mechanism, #923 will allow users to define custom transforms/augmentations and use them in the pipeline.
Describe the feature Please add augmentation "hooks" in configuration that are completely in "user space"
Motivation Currently adding augmentation requires changing mmdetection code. This is not great both because of :
Related resources
Additional context a simple "augmentaion" section in the config with one or more user python functions that will be called with dataset or stage name (to differenciate between val and train for example), image/s to augment. bbox list and segmentaion list, returning images, bbox and seg to be used something like: