amadeuzou / vrn-pytorch

PyTorch Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"
82 stars 23 forks source link

Weights re-trained or transferred from torch #2

Open Jim61C opened 6 years ago

Jim61C commented 6 years ago

Hi!

Firstly, thank you for making the architecture and feedforward code available in py-torch! I am just wondering for the weights, are you copying from the torch t7 model to py-torch or have re-trained the weights using the model definition that you had?

Thank you!

marvin521 commented 6 years ago

Maybe we can talk about the implementation details of training code?

LucienXian commented 5 years ago

@marvin521 hi, how do you train the model?