saslie/rnn_bachelor

Fork: 0

saslie / rnn_bachelor_thesis

2018-04-30	0a9796e Browse files » 2 trained models (5 layer GRU and 5 layer lstm) added and their respective pkl data to allow a full_load() saslie committed on 30 Apr 2018
2018-04-29	60c481d Browse files » Test on second laptop saslie committed on 29 Apr 2018
2018-04-27	697d8a2 Browse files » Smarter checkpoints ... Going back to earlier last checkpoint if persormance was better than at end of training Scalers now work on on 2d and 3d arrays full_load and full_save added which save and restore the rnn with all parameters get_rnn_folder added which is a helper function for full_load and provides the folder name for an architecture with the correct notation Also dataset added Sascha Liechti committed on 27 Apr 2018
2018-04-20	83f29d0 Browse files » Standard scaler (and inverse) added for 2d and 3d arrays of all shapes ... Min Max scaler (and inverse) added for 2d and 3d arrays of all shapes Scalers now also work on test set Huge performance increase Finetuning for patience trigger for scalers missing Trained model for newest version added and old version discarded Sascha Liechti committed on 20 Apr 2018
2018-04-19	f168640 Browse files » Normalization with skicit learn added (Doesnt work on test_set yet) ... Early stopping with patience refined (How to find optimal patience and trigger value?) Elu activation added Last activation i always tanh Checkpoints added Sascha Liechti committed on 19 Apr 2018
2018-04-16	275e721 Browse files » Loss normalized ... Early stopping with patience improved and fine tuned Improved checkpoints Bugfixes Plot of loss added Trained save of rnn_lstm_5l_[50,40,30,20,10] added Sascha Liechti committed on 16 Apr 2018
	f874eb8 Browse files » Early stopping with patience added ... Checkpoints during training added to go back to best state if perfomance decreases Sascha Liechti committed on 16 Apr 2018
	618a744 Browse files » Removed n_layer as with the new ncells its implicitly stated and added Errors if ncells is of the wrong type (has to be int or a list of ints) Sascha Liechti committed on 16 Apr 2018
2018-04-14	6c622e3 Browse files » Delete copy Sascha Liechti committed on 14 Apr 2018
	6705f77 Browse files » Revert "Revert "This is the more advanced version of the old program"" ... This reverts commit `963add1`. saslie committed on 14 Apr 2018
	0069730 Browse files » This is the more advanced version of the old program Added early stopping Improved performance It supports now many layers and an arbitrary amount of cells per layer. It also saves in a folder named after the models architecture Sascha Liechti committed on 14 Apr 2018
	a336e23 Browse files » This is the more advanced version of the old program ... Added early stopping Improved performance It supports now many layers and an arbitrary amount of cells per layer. It also saves in a folder named after the models architecture saslie committed on 14 Apr 2018
	963add1 Browse files » Revert "This is the more advanced version of the old program" ... This reverts commit `ca028c5`. saslie committed on 14 Apr 2018
	ca028c5 Browse files » This is the more advanced version of the old program ... Added early stopping Improved performance It supports now many layers and an arbitrary amount of cells per layer. It also saves in a folder named after the models architecture saslie committed on 14 Apr 2018
2018-04-12	c68bb65 Browse files » Revert "Test for rnn state" ... This reverts commit `82de3ca`. Sascha Liechti committed on 12 Apr 2018
	82de3ca Browse files » Test for rnn state Sascha Liechti committed on 12 Apr 2018
	66ef7f8 Browse files » first test Sascha Liechti committed on 12 Apr 2018
2018-04-11	f735bda Browse files » Add files via upload Sascha Liechti committed on 11 Apr 2018
2018-04-11	a855ba0 Browse files » Initial commit Sascha Liechti committed on 11 Apr 2018