recurrent interface network rin

We have hosted the application recurrent interface network rin in order to run this application in our online workstations with Wine or directly.

Quick description about recurrent interface network rin:

Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and Video without cascading networks, in Pytorch. The author unawaredly reinvented the induced set-attention block from the set transformers paper. They also combine this with the self-conditioning technique from the Bit Diffusion paper, specifically for the latents. The last ingredient seems to be a new noise function based around the sigmoid, which the author claims is better than cosine scheduler for larger images. The big surprise is that the generations can reach this level of fidelity. Will need to verify this on my own machine. Additionally, we will try adding an extra linear attention on the main branch as well as self-conditioning in the pixel space. The insight of being able to self-condition on any hidden state of the network as well as the newly proposed sigmoid noise schedule are the two main findings.

Features:

• Results will be saved periodically to the ./results folder
• Experiment with the RIN and GaussianDiffusion class outside the Trainer
• Implementation of Recurrent Interface Network (RIN)
• Highly efficient generation of images and Video without cascading networks
• This repository also contains the ability to noise higher resolution images more
• Contains the simple linear gamma schedule proposed in the paper

Programming Language: Python.
Categories: