Popular GitHub Repositories for Reusing Discriminators

A library for transfer learning by reusing parts of TensorFlow models.

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Official PyTorch implementation of NICE-GAN: Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation

Pytorch implementation of Image Manipulation with Perceptual Discriminators paper

[NeurIPS 2022] Open source code for reusing prior computational work in RL.

[ICLR 2023] "Learning to Grow Pretrained Models for Efficient Transformer Training" by Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen, Philip Greengard, Leonid Karlinsky, Rogerio Feris, David Cox, Zhangyang Wang, Yoon Kim

UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

[NeurIPS 2021] "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators" by Yunhui Long*, Boxin Wang*, Zhuolin Yang, Bhavya Kailkhura, Aston Zhang, Carl A. Gunter, Bo Li

A comprehensive AI solution for saving, sharing, and reusing code materials in your Sublime Text environment, with a powerful integration of AI assistance and Copilot and many LLM models including ChatGPT functionality, specifically designed to enhance your coding workflow.

A Chrome extension for saving and reusing AI prompts to boost efficiency with quick insertion.

This repository is for profiling, extracting, visualizing and reusing generative AI weights to hopefully build more accurate AI models and audit/scan weights at rest to identify knowledge domains for risk(s).

An AI prompt saving, reusing, and sharing web app built using the FERN tech stack.

Lightweight semantic caching for any LLM-powered application using RedisVL—cut API costs and slash response times by reusing similar past queries

Experimenting with the PPGN-h architecture by adding new discriminators to the layers of the encoder

Smart Waste Management is an AI-driven web application that empowers users to make informed decisions about disposing or reusing waste by using image recognition and natural language assistance.