saslie/rnn_bachelor

Fork: 0

saslie / rnn_bachelor_thesis

History for rnn_bachelor_thesis / 1_to_1_multi_layer.ipynb

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