Lossy PNG compressor — pngquant command based on libimagequant library

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

Neural Networks with low bit weights on low end 32 bit microcontrollers such as the CH32V003 RISC-V Microcontroller and others

🎨 Convert images to 15/16-bit RGB color with dither

off the charts color quantization 🎨

基于FPGA量化的人脸口罩检测

Subband filtering with ADPCM

Color quantization/palette generation for png images

Quantized Memory-Augmented Neural Networks (AAAI-18)

Extremely fast color quantization. Reduce color information of a 24-bit RGB bitmap down to 8-bit.

V-lang api wrapper for llm-inference chatllm.cpp

The purpose of this project is to compare different means of computing convolution operation, and see if naive quantiization actually speed ups operation.

Clean C language version of quantizing llama2 model and running quantized llama2 model

Code and resources for the paper: "Cognitive Radio Spectrum Sensing on the Edge: A Quantization-Aware Deep Learning Approach"

Nim api-wrapper for llm-inference chatllm.cpp

The Quantizer - A Swift-based reimplementation of ImageAlpha

A quantized TensorFlow Lite–based real-time object detection system on ESP32-CAM, optimized with the EON™ Compiler for low-latency, low-memory, and portable AI-IoT deployment.

kotlin api wrapper for llm-inference chatllm.cpp

Code for "Characterising Across Stack Optimisations for Deep Convolutional Neural Networks"

Neural Network C is an advanced neural network implementation in pure C, optimized for high performance on CPUs and NVIDIA GPUs.