swghosh / DeepFace

Keras implementation of the renowned publication "DeepFace: Closing the Gap to Human-Level Performance in Face Verification" by Taigman et al. Pre-trained weights on VGGFace2 dataset.
https://research.fb.com/publications/deepface-closing-the-gap-to-human-level-performance-in-face-verification/
MIT License
194 stars 61 forks source link

LFW accuracy #10

Open serengil opened 4 years ago

serengil commented 4 years ago

Hi,

You should evaluate DeepFace model on LFW data set and share its accuracy on read me page. The original DeepFace study got 97.35% accuracy but your model trained on different data set. It might have different accuracy level.

Similarly, David Sandberg reimplemented Google FaceNet model and evaluate his model on LFW data set as well. He got 0.99650+-0.00252 accuracy whereas original Google FaceNet study got 99.63%.

This will show how your model robust indeed.

Regards.

swghosh commented 4 years ago

Hey @serengil,

That would indeed add to some meaningful additions to the existing work. Look forward to working on it in the coming weeks.