multigeom.diffusion

Diffusion (core, needs diffusers): the conditional diffusion model of an encoder, everything G(x) needs besides the encoder. DiffusionConfig sets the conditioning width from the encoder; the model, the responses of the encoder on images and the training of the model (resumable) are in the submodules.

Modules

config	Configuration of the conditional diffusion model of an encoder.
model	Conditional diffusion model: a UNet2DConditionModel from diffusers augmented with a small response-to-token MLP.
responses	Stage 2: Generate synthetic neural responses for every TinyImageNet image by evaluating the trained encoder f_φ from Stage 1.
train	Stage 3: Train a conditional DDPM on TinyImageNet, conditioned on the synthetic responses produced in Stage 2.