ZeroFidelity

class deepinv.optim.ZeroFidelity

Bases: DataFidelity

Zero data fidelity term \(\datafid{x}{y} = 0\). This is used to remove the data fidelity term in the loss function.

fn(x, y, physics, *args, **kwargs)

This function returns zero for all inputs.

grad(x, y, physics, *args, **kwargs)

This function returns a zero image.

grad_d(u, y, *args, **kwargs)

This function returns a zero image.

prox_d(u, y, *args, **kwargs)

This function returns the input image.

prox_d_conjugate(u, y, *args, **kwargs)

This function returns the input image.

Examples using ZeroFidelity:

Using state-of-the-art diffusion models from HuggingFace Diffusers with DeepInverse

Using state-of-the-art diffusion models from HuggingFace Diffusers with DeepInverse

Building your diffusion posterior sampling method using SDEs

Building your diffusion posterior sampling method using SDEs