Background
Before we can load model weights and run inference on static patches, we need to develop the piping around this model to load and and send input.
Description
Create an interface for a model and define the input / output shape of noise, you will need to do some reasearch into pytorch to figure out what we are expecting input / output to look like.
Create a fake mock diffusion model that uses this interface and have it generate output from noise. This fake must:
- take a noisy patch and returns another patch
- apply some deterministic function to the patch
Changes should live in src/terrain-diffusion/inference.py and tests/test_inference.py
Background
Before we can load model weights and run inference on static patches, we need to develop the piping around this model to load and and send input.
Description
Create an interface for a model and define the input / output shape of noise, you will need to do some reasearch into pytorch to figure out what we are expecting input / output to look like.
Create a fake mock diffusion model that uses this interface and have it generate output from noise. This fake must:
Changes should live in
src/terrain-diffusion/inference.pyandtests/test_inference.py