search

liorshk / facenet_pytorch

PyTorch implementation of the paper "FaceNet: A Unified Embedding for Face Recognition and Clustering"
MIT License
321 stars 90 forks source link

Pre-Trained Models #3

Open ahkarami opened 6 years ago

ahkarami commented 6 years ago

Dear @liorshk, Thank you for your code. Do you have any pre-trained models? Would you please, release the weights of your pre-trained models?

xiaoiker commented 6 years ago

Hi, have you found the pre-trained model or a good way to convert from the tensorflow model to pytorch?

ahkarami commented 6 years ago

@xiaoiker You can use MMdnn or SphereFace.

chungyau97 commented 5 years ago

@ahkarami @xiaoiker I download the pretrain model from https://github.com/davidsandberg/facenet (20180402-114759) Then I install mmdnn Then I run this code mmconvert -sf tensorflow -in model-20180402-114759.meta -df pytorch -om 20180402-114759.pth Error: image

Am I writing it wrong?

@xiaoiker You can use MMdnn or SphereFace.

ahkarami commented 5 years ago

Dear @chungyau97, Thank you for your effort. Really, I didn't do that (i.e., converting the model). You can send an Issue about it in the MMdnn GitHub repository.

chungyau97 commented 5 years ago

@ahkarami I'm curious about the SphereFace. Why do you recommend this?

ahkarami commented 5 years ago

It is just a suggestion. You can refer to its paper for more information.

timesler commented 5 years ago

@xiaoiker @chungyau97 there is a pytorch conversion of the two pretrained inception resnet v1 models (vggface and casia-web face) from davidsandberg/facenet here:

https://github.com/timesler/facenet-pytorch

Disclaimer: it is my repo.