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 |
---|
|
1_to_1_multi_layer.ipynb |
---|
matched_8hittracks.pkl 0 → 100644 |
---|
Not supported
|
trained_models/rnn_model_lstm_leaky_relu_5l_[50,40,30,20,10]c/checkpoint 100644 → 0 |
---|
trained_models/rnn_model_lstm_leaky_relu_5l_[50,40,30,20,10]c/rnn_basic.data-00000-of-00001 100644 → 0 |
---|
Not supported
|
trained_models/rnn_model_lstm_leaky_relu_5l_[50,40,30,20,10]c/rnn_basic.index 100644 → 0 |
---|
Not supported
|
trained_models/rnn_model_lstm_leaky_relu_5l_[50,40,30,20,10]c/rnn_basic.meta 100644 → 0 |
---|
Not supported
|