Shobhit Sharma

Results 7 comments of Shobhit Sharma

@shicaiwei123 is it only depth model or fusion of depth patch?

Yeah have implemented the depth with help of prnet module but again that is not surprising to see the overfitting results..

Got any idea?

> Thanks for wonderful work. However, i would like to train this facemesh model with our own dataset which has 98 keypoints. > Could you please help me how we...

> @showbit01 > Not really, but i was able to train the model by adding BN layer and PFLDLoss, but results are not so good as compare to other state-of-the-art...

> > Yeah have implemented the depth with help of prnet module but again that is not surprising to see the overfitting results.. > > Hi, can u help me...

@hayk314 no,text tokens should be needed as ground truth labels with audio signal as input