Commits · 7c1241ff46ab1fa9179cdae515669af39d59d6c1 · Nikolai.Hartmann / KerasROOTClassification

Aug 14, 2018
- evaluate RNN working · 7c1241ff
  Nikolai.Hartmann authored 6 years ago
  
  7c1241ff
- model and training for RNN working · d09ab3d6
  Nikolai.Hartmann authored 6 years ago
  
  d09ab3d6
- data structuring for RNN working · fe84f351
  Nikolai.Hartmann authored 6 years ago
  
  fe84f351
- remove validate and plot all from train · aa3ffe0a
  Nikolai.Hartmann authored 6 years ago
  
  aa3ffe0a
- put score evaluation in separate function · f8a5e443
  Nikolai.Hartmann authored 6 years ago
  
  f8a5e443
- correct quantile range for input plots · b9419f4d
  Nikolai.Hartmann authored 6 years ago
  
  b9419f4d
- making balanced training more efficient · 5b541afd
  Nikolai authored 6 years ago
  
  5b541afd
- starting to develop yield_batch function for RNN · f52e8ad9
  Nikolai authored 6 years ago
  
  f52e8ad9
- starting rnn wrapper · 9994f0ad
  Nikolai authored 6 years ago
  
  9994f0ad
- making balanced training more efficient · 6409522c
  Nikolai authored 6 years ago
  
  6409522c
Aug 13, 2018
- plot train and test for ROC by default · e543ec8d
  Nikolai authored 6 years ago
  
  e543ec8d
- commenting number of cores for session · cb732b1c
  Nikolai authored 6 years ago
  
  cb732b1c
Aug 12, 2018
- allow both None and 0 for deactivating dropout · f3ce92d9
  Nikolai authored 6 years ago
  
  f3ce92d9
Aug 10, 2018
- try to avoid copying also when fitting scaler · ae08f994
  Nikolai.Hartmann authored 6 years ago
  
  ae08f994
- further memory improvements · 99b7dc94
  Nikolai.Hartmann authored 6 years ago
  
  99b7dc94
- Memory improvements · 0e1202f5
  Nikolai.Hartmann authored 6 years ago
  
  * stop option for reading a maximum number of events for train/test * inplace scaling
  0e1202f5
- Experimental support for initialising from pandas DataFrame (memory intense ...) · beea1cfe
  Nikolai.Hartmann authored 6 years ago
  
  beea1cfe
- starting initialisation from pandas df · 0519ccd8
  Nikolai authored 6 years ago
  
  0519ccd8
- support for tensorboard · 2e9b6f67
  Nikolai.Hartmann authored 6 years ago
  
  2e9b6f67
- include identifiers in to_DataFrame · cfa87567
  Nikolai authored 6 years ago
  
  cfa87567
- adding to_DataFrame function · d1d1cf3c
  Nikolai authored 6 years ago
  
  d1d1cf3c
Aug 09, 2018
- Extended dropout support · b9e191be
  Nikolai.Hartmann authored 6 years ago
  
  b9e191be
- weighted accuracy · d23f0440
  Nikolai authored 6 years ago
  
  d23f0440
Aug 08, 2018
- introduce option to rename branch expressions · a396d67b
  Nikolai authored 6 years ago
  
  a396d67b
Aug 07, 2018
- allow different number of nodes per layer · 87b25c46
  Nikolai.Hartmann authored 6 years ago
  
  87b25c46
Aug 06, 2018
- Implementing WeightedRobustScaler (now default) · 96a77543
  Nikolai.Hartmann authored 6 years ago
  
  96a77543
- Allow reoder=True in auc if values are not increasing (due to neg event weights) · 7058afbf
  Nikolai.Hartmann authored 6 years ago
  
  7058afbf
Jul 27, 2018
- abspath for data dir · 78278114
  Nikolai.Hartmann authored 6 years ago
  
  78278114
- xlim parameter for plot_score · be03412d
  Nikolai.Hartmann authored 6 years ago
  
  be03412d
- loss function configurable · d9f78c70
  Nikolai.Hartmann authored 6 years ago
  
  d9f78c70
- ylim option for plot_score · a027593b
  Nikolai.Hartmann authored 6 years ago
  
  a027593b
- switch to np.digitize for histogram error calculation · cebf5f26
  Nikolai authored 6 years ago
  
  cebf5f26
Jul 24, 2018
- ensure that the model weights end up in project_dir · d665c504
  Nikolai authored 6 years ago
  
  d665c504
- model checkpoint options · 5c7cd191
  Nikolai authored 6 years ago
  
  option to set modelcheckpoint options
  5c7cd191
- make bins orthogonal in get_bin_centered_hist · 6300dafe
  Nikolai authored 6 years ago
  
  6300dafe
Jul 23, 2018
- more options for overlay functions - multiple projects in browsing script · 99f3359d
  Nikolai.Hartmann authored 6 years ago
  
  99f3359d
- ylim option for loss plot · 3432c091
  Nikolai.Hartmann authored 6 years ago
  
  3432c091
Jun 19, 2018
- Close figures after plotting · 9db4ffce
  Nikolai.Hartmann authored 6 years ago
  
  9db4ffce
Jun 18, 2018
- use step size to normalise backgrounds and signal for significance scan · 80bbfbbb
  Nikolai.Hartmann authored 6 years ago
  
  80bbfbbb
Jun 13, 2018
- python3 compatibility · 772956b7
  Nikolai authored 6 years ago
  
  772956b7