RayanWang / Speech_emotion_recognition_BLSTM

Bidirectional LSTM network for speech emotion recognition.
MIT License
260 stars 78 forks source link

Test Accuracy #6

Closed hirunifernando closed 6 years ago

hirunifernando commented 6 years ago

Hi RayanWang, I have started the model training with the use of find_best_model.py.Below validation accuracy was achieved. While the training process is ongoing 200 epochs, highest validation accuracy was 0.5652(early stopping at 35)

While the training process is ongoing 100 epochs, highest validation accuracy was 0.3354(early stopping at 19) I want to increase the testing accuracy more (at least 70).what are additional things and modifications should I follow. Thank u.

RayanWang commented 6 years ago

First of all, these two results may sound strange. Maybe depend on your optimizer or other hyper parameter you tuned. I recommend using cross-validation first to confirm if the data set is sufficient and correct.

hirunifernando commented 6 years ago

After finishing the training process, max accuracy was achieved as 58. I want a high accuracy model to predict emotions. So If u can plz send me the trained model which have accuracy around 68. Thank u for ur support