burke86
commented
2 years ago Hi Pierluigi,
Yes, you will likely need to train on your own data to get the best results. You would need a training set of images and masks (e.g., from sextractor or sep) first. I suggest you follow our new code here (https://nbviewer.org/github/burke86/astrodet/blob/main/demo_decam.ipynb) and the repo here still under construction (https://github.com/burke86/astrodet), which is much easier to follow and uses the detectron2 library.
You can also try the panoptic segmentation modes in detectron2 for background detection.
Hope that helps, and feel free to ask us more questions.
Colin
On Feb 15, 2022, at 10:50 AM, Pierluigi Rinaldi @.**@.>> wrote:
Hi all,
Maybe it is a dumb question, but it is my first time playing with deep learning codes.
To use this code, should I train the neural network on my images? My final goal would be to create, given an image in a given band, a mask to mask sources out (galaxies and stars) in order to deal with the background only.
Thanks in advance
— Reply to this email directly, view it on GitHubhttps://urldefense.com/v3/__https://github.com/burke86/astro_rcnn/issues/10__;!!DZ3fjg!pIM1Gh5OzAtVHiYn6YeC3ne1Yv9YZrHIABiFCcSmBuYOF_0hz_uE6PkuSR1SPeEyyATg$, or unsubscribehttps://urldefense.com/v3/__https://github.com/notifications/unsubscribe-auth/ADKDILOR5DE5TD736KITBNTU3J73ZANCNFSM5OPDA4ZA__;!!DZ3fjg!pIM1Gh5OzAtVHiYn6YeC3ne1Yv9YZrHIABiFCcSmBuYOF_0hz_uE6PkuSR1SPaX2mfrV$. Triage notifications on the go with GitHub Mobile for iOShttps://urldefense.com/v3/__https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675__;!!DZ3fjg!pIM1Gh5OzAtVHiYn6YeC3ne1Yv9YZrHIABiFCcSmBuYOF_0hz_uE6PkuSR1SPXo0CSU7$ or Androidhttps://urldefense.com/v3/__https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign*3Dnotification-email*26utm_medium*3Demail*26utm_source*3Dgithub__;JSUlJSU!!DZ3fjg!pIM1Gh5OzAtVHiYn6YeC3ne1Yv9YZrHIABiFCcSmBuYOF_0hz_uE6PkuSR1SPUb5-qRX$. You are receiving this because you are subscribed to this thread.Message ID: @.***>
Hi all,
Maybe it is a dumb question, but it is my first time playing with deep learning codes.
To use this code, should I train the neural network on my images? My final goal would be to create, given an image in a given band, a mask to mask sources out (galaxies and stars) in order to deal with the background only.
Thanks in advance