Trainning loss around 0.08?

[YuTingLiu]

Thanks for share this unbelivable projects. We are family// Since I decided to train my own model, uv map generating has been done, data comes form 300W-LP, which contains 122450 samples.

• What I am not sure is the trainning loss always around 0.08, output as follow: Can someone tell me how this happen?

[YuTingLiu]

Solved and closed, thanks.

[YuTingLiu]

This is result after 3k iters, kinds of scary. Anyway, the .obj file predicted by pre-trainned model all the same.

[HBLucasKo]

@YuTingLiu Hi!! Could you tell me how you solved the issue??

[qiannvMao]

@YuTingLiu Hi,as a newer to this, I failed to achieve the training code, could you please provide training code to me? I hope I can get your help, thank you very much. My email: [email protected]

[michaelhuang74]

@YuTingLiu Hi Yuting, where did you get the training code or did you write the code by yourself? I also like to train the model using new datasets. Do you mind share your training code with me? Thanks a lot. My email is [email protected]

[JianBin-Liu]

Thanks for share this unbelivable projects. We are family// Since I decided to train my own model, uv map generating has been done, data comes form 300W-LP, which contains 122450 samples.

• What I am not sure is the trainning loss always around 0.08, output as follow: Can someone tell me how this happen? my trainning loss always around 2.00, did I need to train consistently?

[JianBin-Liu]

Thanks for share this unbelivable projects. We are family// Since I decided to train my own model, uv map generating has been done, data comes form 300W-LP, which contains 122450 samples.

• What I am not sure is the trainning loss always around 0.08, output as follow: Can someone tell me how this happen? my trainning loss always around 2.00, did I need to train consistently?