Ismael Mendoza

Consider DC2 matching -> check magnitude of objects (something like a safety check) Or use a different distance metric

Biswajit: A function that takes in individual images and blended images and computes the metrics. A basic function that does not take the matches.

This has been done in the scarlet side, @thuiop maybe now you can try to revive the notebook in scarlet with this tag? (and potentially add it to one of...

agreed - I didn't think it warranted holding up this issue much longer, thanks for your suggestion

The solution is probably to make the test slower by having more sources. Not sure if this is a good idea.

Hi @sowmyakth , I like this idea, could you elaborate a bit on what it involves or where you thinking of incorporating this FOF algorithm for the blends?

See also this notebook: https://github.com/LSSTDESC/DC2-analysis/blob/master/tutorials/matching_fof.ipynb

Thanks @enourbakhsh and @fjaviersanchez for your suggestions!

This sounds like a good idea, what do you think @sowmyakth ? I was thinking that good places to start would be `generate` in `measure.py` and in `draw_blends.py`.

Thinking about this some more, I realized it might be useful to add this feature but let it be optional as to not enforce `tensorflow` or `pytorch` as a requirement...