"Deep Generative Modeling": Introductory Examples

A collection of tools for neural compression enthusiasts.

Bare-bones implementations of some generative models in Jax: diffusion, normalizing flows, consistency models, flow matching, (beta)-VAEs, etc

Curated list of papers and resources focused on neural compression, intended to keep pace with the anticipated surge of research in the recent years.

Official code for "Computationally-Efficient Neural Image Compression with Shallow Decoders", ICCV 2023

A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.

JPD-SE: High-Level Semantics for Joint Perception-Distortion Enhancement in Image Compression

Exploring advanced autoencoder architectures for efficient data compression on EMNIST dataset, focusing on high-fidelity image reconstruction with minimal information loss. This project tests various encoder-decoder configurations to optimize performance metrics like MSE, SSIM, and PSNR, aiming to achieve near-lossless data compression.

An unofficial replication of NAS Without Training.