| ... | ... | @@ -398,9 +398,9 @@ Meeting ID: 860 7262 9011 Password: 001303 |
|
|
|
### Action items:
|
|
|
|
|
|
|
|
* [x] simplify/optimise the learning rate scheduler in densenets training.
|
|
|
|
* [ ] write script for systematic BLU calculation and plots for the O3 real events.
|
|
|
|
* [x] write script for systematic BLU calculation and plots for the O3 real events.
|
|
|
|
* [x] retrain densenets using whitened QTs, wider qrange etc.
|
|
|
|
* [ ] optimise XGB with QTs with, more info, missing data etc. [script](https://git.ligo.org/srashti.goyal/lensid/-/blob/master/development/optimise_densenets.py) [notebook](https://git.ligo.org/srashti.goyal/lensid/-/blob/master/development/optimise_XGB_QTs.ipynb)
|
|
|
|
|
|
|
|
* [x] Ask lensing group for the O3b representative psd.
|
|
|
|
* [ ] Gather injection parameters for O3b background from Apratim.
|
|
|
|
* [x] It seems that the dimensions of Healpix grid for bayestar skymaps is same. Compare the overlap and other statistic with the current cartesian map method to the bayestar-skymap-flatten skymap method.
|
| ... | ... | @@ -428,7 +428,6 @@ Meeting ID: 860 7262 9011 Password: 001303 |
|
|
|
### Action items:
|
|
|
|
|
|
|
|
* [x] Look into skymap calculations, theta to declination conversion as JR pointed out.
|
|
|
|
* [ ] Produce a better version of results as soon as possible.
|
|
|
|
* [x] Wrap up the code review.
|
|
|
|
|
|
|
|
## 3 December 2021
|
| ... | ... | @@ -442,7 +441,15 @@ Meeting ID: 860 7262 9011 Password: 001303 |
|
|
|
|
|
|
|
* [ ] Fix learning rates for densenets as JR suggested.
|
|
|
|
* [ ] Compare ML FPP and BLU FPP with [GOLUM's CLU](https://docs.google.com/spreadsheets/d/1wrpzwudP1MbraJNlCB6arnTCzbeuCPLBx16eReMdQvM/edit#gid=899668020)
|
|
|
|
* [ ] Share updated results with Justin, after optimisation perhaps.
|
|
|
|
* [ ] Figure out why the unlensed pairs FPP in O3a background and in test set is not going below 1e-3, whereas test lensed pairs is going upto 1e-5.
|
|
|
|
* [ ] Produce whitened QTs results.
|
|
|
|
* [x] Share updated results with Justin, after optimisation perhaps.
|
|
|
|
* [x] Figure out why the unlensed pairs FPP in O3a background and in test set is not going below 1e-3, whereas test lensed pairs is going upto 1e-5.
|
|
|
|
* [x] Produce whitened QTs results.
|
|
|
|
* [ ] optimise XGB with QTs with, more info, missing data etc. [script](https://git.ligo.org/srashti.goyal/lensid/-/blob/master/development/optimise_densenets.py) [notebook](https://git.ligo.org/srashti.goyal/lensid/-/blob/master/development/optimise_XGB_QTs.ipynb)
|
|
|
|
|
|
|
|
## 10 December 2021
|
|
|
|
* The O3 results status update [page](https://git.ligo.org/srashti.goyal/lensid-ml-o3/-/wikis/O3-result-updates)
|
|
|
|
* Discuss about the plots and FPPs going to the paper.
|
|
|
|
* Corner plots for the image pairs.
|
|
|
|
|
|
|
|
### Action items:
|
|
|
|
* [ ] Write a script or notebook for investigating a particular pair. |
|
|
\ No newline at end of file |
