README.md 768 Bytes
Newer Older
Marius Kriegerowski's avatar
Marius Kriegerowski committed
1 2 3 4
Prereqs
-------

 - tensorflow
Marius Kriegerowski's avatar
Marius Kriegerowski committed
5
 - scikit-optimize
Marius Kriegerowski's avatar
Marius Kriegerowski committed
6 7
 - git clone git@github.com:HerrMuellerluedenscheid/swarming.git

Marius Kriegerowski's avatar
Marius Kriegerowski committed
8 9 10 11 12 13 14 15 16 17 18 19 20
Invoke
------

To start training:

    pinky --config <config_filename> --train

You can dump your examples to TFRecordDatasets to accelerate io operations:

    pinky --config <config_filename> --write <new_config_filename>

and use the newly created config file to run `--train`

Marius Kriegerowski's avatar
upd  
Marius Kriegerowski committed
21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36

Tests
-----

 - basic learning (synthetics, real data)
 - synthetics, layered cake, train with top and bottom layer containing events.
        Validate with events within middle layer
 - test extrapolation with fault plane geometry
 - synthetic pretraining
 - hyperparameter optimization using skopt

Outlook
-------

 - increase z error weight -> improve z estimates