Still having troubles getting the positron ratio for runs with a raster. When I now include the raster I get
Before:
For a run with the raster on (73006) I get
Before:
I suspect that something funny is happening in the training. Need to re-check simulation/training scripts. The width at the target compared to the "no raster" reconstruction does not make sense. Improvement to the "energy correction" network could likely fix this.


New neural networks:

To do:


Other things:

[ICO]NameLast modifiedSizeDescription

[PARENTDIR]Parent Directory   -  
[IMG]positron_id6_c2_7300..>2015-01-09 17:56 1.0M 
[IMG]positron_id2_73006_n..>2015-01-09 17:56 32K 
[IMG]positron_id2_73006.png 2015-01-09 17:56 33K 
[IMG]positron_id2_72994_r..>2015-01-09 17:56 31K 
[IMG]positron_id2_72994_l..>2015-01-09 17:56 30K 
[IMG]positron_id2_72994_O..>2015-01-09 17:56 30K 
[IMG]positron_id2_72994.png 2015-01-09 17:56 31K 
[IMG]dis_diff_xsec_nucleu..>2015-01-09 17:56 15K 
[IMG]asym_vs_run-30.png 2015-01-09 17:56 27K 
[IMG]NNParaElectronXYCorr..>2015-01-09 17:56 143K 
[IMG]NNParaElectronXYCorr..>2015-01-09 17:56 63K 
[IMG]NNParaElectronXYCorr..>2015-01-09 17:56 66K 
[IMG]NNParaElectronAngleC..>2015-01-09 17:56 41K 

Apache/2.4.62 (Red Hat Enterprise Linux) Server at hallcweb.jlab.org Port 443