multimodal-masking

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Extension for Automatic1111 and ComfyUI to automatically create masks for Background/Hair/Body/Face/Clothes in Img2Img

Terraform utility to mask select output from `terraform plan` and `terraform apply`

[ICML 2023] Official PyTorch Implementation of "Hierarchical Neural Coding for Controllable CAD Model Generation".

Implementation of Zorro, Masked Multimodal Transformer, in Pytorch

Remap, mask, renumber, unique, and in-place transposition of 3D labeled images. Point cloud too.

Adobe-EntitySeg dataset

This is an implementation of paper "End-to-end Speech Translation via Cross-modal Progressive Training" (Interspeech2021)

Complex Ideal Ratio Mask (CIRM)

This data pipeline is built upon the AWS Cloud Infrastructure and uses Streamlit as a front-end for user input.