Difference: JetFlavourTagging (17 vs. 18)

Revision 182013-07-26 - DanProtopopescu

Line: 1 to 1

META TOPICPARENT	name="WebHome"

Jet Flavour Tagging Howto

Line: 50 to 50

The processors listed above could be run in sequence, or split in several steps, invoking a LCIOOutput processor to write intermediate slcio outputs at every step. Here's a script for that, where the intermediate xml files are slight modifications of the files provided in LCFIVertex/steering examples. We found that the most time-consuming processor is ZVTOP_ZVRES with more than 10 s/event.

Changed:

<
< We found it easier to run processors 1 to 6 on batches of 10 input files, and save the outputs as zvresX_out.slcio. Then we ran processors 7 and 8 on these files to produce a new set ftiX_out.slcio. We used all these to train the neural net, but then again was easier to run flavour tagging (see below) on the individual ftiX_out.slcio files. Again we used all files for the purity vs. efficiency plots (see below).

>
> We found it easier to run processors 1 to 6 on batches of 10 input files, and save the outputs as /afs/phas.gla.ac.uk/data/ilc/datasets01/1.4tev/ZVRES_out/runX_out.slcio. Then we ran processors 7 and 8 on these files to produce a new set ftiX_out.slcio. We used half of these files to train the neural net, but then again was easier to run flavour tagging (see below) on the individual ftiX_out.slcio files. We used the other half of the files files for the purity vs. efficiency plots (see below). These slcio output files were stored in /afs/phas.gla.ac.uk/data/ilc/datasets01/1.4tev/ZVRES_out/ as well.

Troubleshooting: The b3_D0CutValue parameter of the IPRPCutProcessor was set to 5O instead of 50, and was causing a crash. For the ZVRESRPCut processor, h1_MCPIDEnable had to be set to false. See also this post

Neural Network Training

Changed:

<
< In the previous step, we have extracted the discriminating parameters and truth-tagged the jets. The slcio files created contain the collections Durham_4Jets, FlavourTagInputs and TrueJetFlavour_4Jets, which we will use now to train our neural nets. We use a customised version of the NeuralNetTrainer code included in the LCFI package. Separate nets were trained for 1, 2, or 3+ vertices to identify b-jets, c-jets, and c-jets with b background. Our steering file contains only:

>
>

In the previous step, we have extracted the discriminating parameters and truth-tagged the jets. The slcio files created are stored in:

/afs/phas.gla.ac.uk/data/ilc/datasets01/1.4tev/ZVRES_out/

These files contain the collections Durham_4Jets, FlavourTagInputs and TrueJetFlavour_4Jets, which we will use now to train our neural nets. We use a customised version of the NeuralNetTrainer code included in the LCFI package. Separate nets were trained for 1, 2, or 3+ vertices to identify b-jets, c-jets, and c-jets with b background. Our steering file contains only:

  <processor name="MyNeuralNetTrainer" type="GlasgowNeuralNetTrainer"/>

Line: 126 to 130

Added:

>
>

Adding background

Up to now all that input slcio files contained was signal, so the 'background' in the plots above is not really background. To add background, we've downloaded 1.4!TeV eeqq files to:

/afs/phas.gla.ac.uk/data/ilc/datasets01/1.4tev/qq/ILD/DST/00002091/000/

We had to run processors 1-7 on these files to identify jets and calculate the discriminating parameters. The resulting outputs, containing approximately 25k events, are stored in /afs/phas.gla.ac.uk/data/ilc/datasets01/1.4tev/ZVRES_out/ as well.

Useful Links

LCFIVertex Tutorial: http://www-pnp.physics.ox.ac.uk/~hillert/VP/LCFIVertex-v00-01/Tutorials.html

View topic | History: r30 < r29 < r28 < r27 | More topic actions...