dunnbc22 / vision_audio_and_multimodal_projects Goto Github PK

Hey Nice work on Speech Emotion Detection with Crema and TESS, I'm curious if you carried out similar experiment with Revdess as well. I'm having trouble getting val loss to decrease on Revdess.

Any comments will be helpful. Thanks!

Your dataset has twice the number of examples as the original Tobacco3482 dataset downloaded from Kaggle. When I downloaded the dataset from Kaggle, there was a copy of the Tobacco3482-jpg directory within the Tobacco3482-jpg directory itself so its likely that you had duplicates. Since train_test_split is random, its likely that you were testing on training data so your results are unfortunately likely biased.

Edit: I looked at your v2 and it correctly has 3482. So the train-test overlap likely explains the performance improvement.

this repository gives me much help for learning, i appreciate it.