Commit Graph

46 Commits

Author SHA1 Message Date
d97785f646 replace softmax by sigmoid in final layer, also adjust dataset for that 2017-07-30 12:50:26 +02:00
b0da2de0ea move utils functions to new file 2017-07-29 19:47:02 +02:00
820a5d1a4d add new network architecture - server label moves to the middle 2017-07-29 19:42:36 +02:00
8cd1023165 replace pca reduction by sklearn's truncated svd 2017-07-29 19:41:14 +02:00
2593131e9e add embedding visualization and domain encoding generator 2017-07-29 10:43:59 +02:00
c1535b941b remove max pooling from models for better infromation flow 2017-07-28 17:25:08 +02:00
18b60e1754 add extended test mode for embeddings 2017-07-17 19:30:56 +02:00
79fc441fe1 wip 2017-07-17 08:44:58 +02:00
d33c9f44ec fix chunks per user function bug caused by numpy version of array_split 2017-07-16 18:49:14 +02:00
844494eca9 add multi-threading for pre-processing 2017-07-16 09:42:52 +02:00
336be37032 fix network props, add PCA to visualize main 2017-07-14 21:01:08 +02:00
6b787792db add custom class weights based on sklearn balance 2017-07-14 15:57:52 +02:00
b35f23e518 add visualization for training curves, pr, roc 2017-07-14 14:58:17 +02:00
d0418b9efa fix hyperband adding h5data and remove param sample 2017-07-12 15:18:45 +02:00
2afaccc84b refactor argparser into separate file, add logger 2017-07-12 10:25:55 +02:00
9f0bae33d5 refactor dataset generation, add callbacks 2017-07-11 21:06:58 +02:00
a196daa895 add simple flow feature extraction function 2017-07-11 13:46:25 +02:00
522854ee0d add h5 support for pauls best config main 2017-07-11 11:12:03 +02:00
41b38de1ab add feature: generate and use h5 data 2017-07-09 23:58:08 +02:00
fdc03c9922 add h5py example 2017-07-08 17:46:07 +02:00
4a9f94a029 add output for main_test 2017-07-08 15:04:58 +02:00
21b9d7be73 merged 2017-07-08 13:04:07 +02:00
36cdba3fdf add pauls config test (TMP) 2017-07-08 13:01:58 +02:00
a3324b5e04 add pauls config test (TMP) 2017-07-08 11:53:51 +02:00
be56112b33 added params 2017-07-07 16:59:08 +02:00
3c4be52bb6 refactor main functions - separate things into different functions 2017-07-07 08:43:16 +02:00
933f6bf1d7 add feature to use both hits information from dataset 2017-07-06 16:27:47 +02:00
b2f5c56019 refactor dataset generation 2017-07-05 21:19:19 +02:00
772b07847f WPI 2017-07-05 19:16:03 +02:00
a70d1cb03a fix: replace X_tr by its elements; choose selected samples for training data too 2017-07-05 18:37:29 +02:00
7c05ef6a12 refactor models package: create separate modules for pauls and renes networks 2017-07-05 18:10:22 +02:00
3862dce975 added new networks for domain embedding and classification task 2017-07-05 17:37:08 +02:00
59c1176e85 refactor network to use new input format 2017-07-04 20:42:48 +02:00
5743127b7f new dataset format: multi-lists -> two arrays 2017-07-04 09:18:50 +02:00
5f8a760a0c added some argparse arguments to main 2017-07-03 13:48:12 +02:00
c972963a19 network predicts 2 by 2 classes, refactored threshold to main 2017-06-30 18:43:50 +02:00
8334e9a84f removed ys from training data generation 2017-06-30 17:42:18 +02:00
deac7f9e58 removed old files from paul 2017-06-30 17:21:03 +02:00
d19036a611 added pauls extensions for new predictions 2017-06-30 17:19:04 +02:00
9768f1546b dataset generation script 2017-06-30 10:49:49 +02:00
7ae68cc30e WIP 2017-06-30 10:42:21 +02:00
bbd63fd1da separating logical sections into dataset, models and main.
continued initial refactoring
2017-06-30 10:12:20 +02:00
be273d9247 refactoring and adding standard files for .gitignore and .keep in data 2017-06-30 09:04:24 +02:00
87b927cdc9 reformat code 2017-06-29 09:19:36 +02:00
d069717
24d677e101 added pauls scripts 2017-06-27 20:29:19 +02:00
René Knaebel
3121729464 Init repo 2017-06-27 20:01:09 +02:00