diksham-flwls issues

Repositories
Issues
Comments

Results 4 issues of


                                            diksham-flwls

Model overfitting when finetuned on smaller data

Hi I am trying to finetune the model on a smaller dataset of 450 samples of greyhead renders that look like this My training loss seems to be converging but...

Evaluation with datasets without audio

This might be a dumb question but how did you evaluate the algorithm on FF++ which does not have audio.

region awareness loss

https://github.com/AaronComo/LipFD/blob/c2a73242c36f604ae7377d77b94c00faf9d942fd/models/LipFD.py#L40 The loss value needs to be averaged across the time dimension as well as otherwise this will blow up the loss value for RA Loss and overpower the BCE...

Model always predicting as fake

I am trying to run the model on a few samples from DeeperForensics and LRW samples. The predictions from the model are heavily skewed towards fake. ```{'Deepfakes': 1.0, 'LRW': 0.5454545617103577,...