Commit Graph

38 Commits

Author SHA1 Message Date
4fc2f0c925 extract weighting function 2017-11-10 10:18:13 +01:00
903e81c931 remove identical parameter from data loading function; add runs argument 2017-11-07 20:47:41 +01:00
826357a41f refactor network models; remove depths 2017-11-07 20:32:08 +01:00
e12bbda8c5 move model creation back into models package 2017-11-07 20:09:20 +01:00
b1f48c1895 add soft parameter sharing network 2017-11-06 21:51:49 +01:00
7b8dfcebbe add long final implementation 2017-11-05 22:52:50 +01:00
a860f0da34 refactor server training into separate file; add additional info to hyperband log 2017-10-19 17:37:29 +02:00
d1da3d6ca3 fix model selection 2017-10-09 15:10:15 +02:00
a686f147f0 add bulk embedding visualization and deep1 network 2017-10-09 14:19:01 +02:00
0b26c6125c fix flat 2 model bug caused by changing input layer 2017-10-06 16:36:58 +02:00
508667d1d0 add server classification model 2017-10-05 15:26:53 +02:00
371a1dad05 add hyperband savefile config, minor change of parameter name 2017-10-03 18:58:54 +02:00
68254d6629 add load function for hyper band results 2017-10-02 07:34:04 +02:00
605447440f refactor hyperband implementation 2017-09-29 22:59:57 +02:00
607d74998c add tsne (does not work with big data)
fix model loading with custom selu function
2017-09-22 10:01:12 +02:00
e2bf2dc90f fix missing parameters, add flat network structure, make larger graphics 2017-09-20 14:43:28 +02:00
fbe6d6a584 remove input shape of first conv layer in networks because unnecessary
add selu activation to deeper network designs
2017-09-17 17:26:09 +02:00
7f49021a63 refactor training - separate staggered training; make differences as small as possible 2017-09-12 08:36:23 +02:00
6ce8fb464f remove reguliarizer on dense too 2017-09-11 16:48:49 +02:00
6121eac448 remove regularizer for conv and domain 2017-09-10 23:40:14 +02:00
1cf62423e1 add regularization to small networks, fix model name in args, fix visualizations 2017-09-10 18:06:40 +02:00
595c2ea894 change argument interface
- add more properties for network specification
 - change names for consistency
2017-09-07 15:53:58 +02:00
5bd8e41711 add staggered model training for intermediate sever prediction; refactor model return values 2017-09-07 14:24:55 +02:00
ed4f478bad add parser argument for naming in multi model modes, minor fixes, 2017-09-05 12:40:37 +02:00
dc9180da10 refactor visualization, change arguments for model type and its depth 2017-09-01 10:42:26 +02:00
5a02f582cd change model - add dense before server output in new model
add some new run scripts
2017-08-05 09:33:07 +02:00
1e781d5491 add argument for model outputs
BUG: need to check --new_model --model_output server
2017-08-02 12:58:09 +02:00
ebaeb6b96e move vocab_size into implementation (not user dependent) 2017-07-30 13:47:11 +02:00
d97785f646 replace softmax by sigmoid in final layer, also adjust dataset for that 2017-07-30 12:50:26 +02:00
820a5d1a4d add new network architecture - server label moves to the middle 2017-07-29 19:42:36 +02:00
c1535b941b remove max pooling from models for better infromation flow 2017-07-28 17:25:08 +02:00
336be37032 fix network props, add PCA to visualize main 2017-07-14 21:01:08 +02:00
b35f23e518 add visualization for training curves, pr, roc 2017-07-14 14:58:17 +02:00
36cdba3fdf add pauls config test (TMP) 2017-07-08 13:01:58 +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
7c05ef6a12 refactor models package: create separate modules for pauls and renes networks 2017-07-05 18:10:22 +02:00