| Geant4 Cross Reference |
1 This repository contains the set of scripts us
2 in this example.
3
4 - root2h5.py: translation of ROOT file with sh
5 - core/constants.py: defines the set of common
6 - core/model.py: defines the VAE model class a
7 - utils/preprocess.py: defines the data loadin
8 - utils/hyperparameter_tuner.py: defines the H
9 - utils/gpu_limiter.py: defines a logic respon
10 - utils/observables.py: defines a set of obser
11 - utils/plotter.py: defines plotting classes r
12 - train.py: performs model training.
13 - generate.py: generate showers using a saved
14 - observables.py: defines a set of shower obse
15 - validate.py: creates validation plots using
16 - convert.py: defines the conversion function
17 - tune_model.py: performs hyperparameters opti
18
19 ## Getting Started
20
21 `setup.py` script creates necessary folders us
22
23 ```
24 python3 setup.py
25 ```
26
27 ## Full simulation dataset
28
29 The full simulation dataset can be downloaded
30
31 If custom simulation is used, the output of fu
32
33 ## Training
34
35 In order to launch the training:
36
37 ```
38 python3 train.py
39 ```
40
41 You may specify those three following flags. I
42
43 ```--max-gpu-memory-allocation``` specifies a
44 an integer.
45
46 ```--gpu-ids``` specifies IDs of physical GPUs
47 If you specify more than one GPU then automati
48 training.
49
50 ```--study-name``` specifies a study name. Thi
51 directory for saving models.
52
53 ## Hyperparameters tuning
54
55 If you want to tune hyperparameters, specify i
56 parameters: discrete, continuous and categoric
57 the categorical parameter requires a list of p
58
59 ```
60 python3 tune_model.py
61 ```
62
63 If you want to parallelize tuning process you
64 setting `--storage="URL_TO_MYSQL_DATABASE"`. T
65
66 ```
67 python3 tune_model.py --storage="URL_TO_MYSQL_
68 ```
69
70 Similarly to training procedure, you may speci
71 ```--study-name```.
72
73 ## ML shower generation (MLFastSim)
74
75 In order to generate showers using the ML mode
76 and angle of the particle and the epoch of the
77 specified (by default is set to 10.000):
78
79 ```
80 python3 generate.py --geometry=SiW --energy=64
81 ```
82
83 If you do not specify an epoch number the base
84
85 ## Validation
86
87 In order to validate the MLFastSim and the ful
88 geometry, energy and angle of the particle:
89
90 ```
91 python3 validate.py --geometry=SiW --energye=6
92 ```
93
94 ## Conversion
95
96 After training and validation, the model can b
97 use `convert.py` script:
98
99 ```
100 python3 convert.py --epoch 1000
101 ```