Skip to content

Neural Architecture Search (NAS) on a UNet neural network (SR3) to optimize for minimal FLOPs and inference latency; while working in a denoising diffusion generative framework (DDPM)

Notifications You must be signed in to change notification settings

jaideepheer/MTech-IITJ-RCAI

Repository files navigation

M.Tech AI Final Project

See: Presentation.pdf and Report.pdf for detailed information.

This work is focused at performing Neural Architecture Search (NAS) on a UNet neural network (SR3) to optimize for minimal FLOPs and inference latency; while working in a denoising diffusion generative framework (DDPM).

The task is image super-resolution on DIV2K dataset for 64x64->128x128 patches.

Broadly, this work mainly draws inspiration from the following papers,

About

Neural Architecture Search (NAS) on a UNet neural network (SR3) to optimize for minimal FLOPs and inference latency; while working in a denoising diffusion generative framework (DDPM)

Topics

Resources

Stars

Watchers

Forks