Alisa-de

would it be possible to replace gradient(calculated from autograd function) backpropagation by scalar loss backpropagation?

2

Hello, I am currently using your code for surface normal estimation. I was wondering what is the benefit to calculate gradient(df) in loss function and do output.backward(gradient=df) in training process...

Hello, may I ask which kind of license you would like to apply for this project? If that is possible, could you please add license to it? Thank you in...