Visualize Denoised Image During Training #1830
Description
Describe the task. Describe the task. It can be a feature, a set of experiments, documentation, etc.
To train a diffusion model means to train the denoiser. At inference, this is used to gradually denoise the image in the inference function. This issue focuses on generating denoised images during training, where the inference function is never called, mainly to debug the diffusion engine whose loss is not currently converging. Note that the denoised tensor has to be decoded before it can be visualized...
Hedgedoc URL, if you are keeping notes, plots, logs in hedgedoc.
No response
URL to the design document
No response
Area
- datasets, data readers, data preparation and transfer
- model
- science
- infrastructure and engineering
- evaluation, export and visualization
- documentation