Shan E Ahmed Raza

We are working on a new design for engines in #578. For now you can look at scale_factor while converting the annotations https://github.com/TissueImageAnalytics/tiatoolbox/blob/336d5e53a3f597125a442e5d6a3148944eca1e60/tiatoolbox/utils/misc.py#L894

We are working on improving the structure of engines in #578

> We are working on improving the structure of engines in #578 The patch mode should still work as `NucleusInstanceSegmentor` is inheriting from `SemanticSegmentor` [[doc](https://tia-toolbox.readthedocs.io/en/latest/_modules/tiatoolbox/models/engine/nucleus_instance_segmentor.html#NucleusInstanceSegmentor)]

Thanks Abdullah. However, we will merge #737 first before working on this PR.

This issue seems to be created due to this PR https://github.com/scikit-learn/scikit-learn/pull/17433. We need to create an issue on https://github.com/scikit-learn/scikit-learn/

> Dear @shaneahmed > > I revised the code to make the input to all models consistent with `num_output_channels` argument. In particular, I changed MicroNet argument to `num_output_channels` but for...

Hi @GeorgeBatch , we plan to make a release v 1.6.0 as soon as #825 or #716 are ready. Probably by end of July/early Aug.

Thanks @GeorgeBatch. That's great. If you can provide us with a sample tif then we can upload this to our servers and set up automated tests. We can also investigate...

> @shaneahmed, I will try to get you access to one of our images as soon as possible. They come from an ongoing study so I might need to request...

Updated branch with develop to fix integration with codecov.