Stars
Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".
OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks
Strong and Open Vision Language Assistant for Mobile Devices
Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"
Python bindings for FFmpeg - with complex filtering support
[CVPR2023] Code for the paper, TriDet: Temporal Action Detection with Relative Boundary Modeling
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
Efficient AI Backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
OpenMMLab Model Compression Toolbox and Benchmark.
An End-to-End Architecture for Keyword Spotting and Voice Activity Detection
A lightweight, simple-to-use, RNN wake word listener
Implementations of Recent Papers in Computer Vision
Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019), "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020) and “Manifold Regularized Dynamic Ne…
📖 Uncle小说,PC版,一个全网小说下载器及阅读器,目录解析与书源结合,支持有声小说与文本小说,可下载mobi、epub、txt格式文本小说。
Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"
A simple high performance CUDA GEMM implementation.
An open source re-implementation of Diablo 2
differentiable sparsity allocation for budgeted pruning
📚 C/C++ 技术面试基础知识总结,包括语言、程序库、数据结构、算法、系统、网络、链接装载库等知识及面试经验、招聘、内推等信息。This repository is a summary of the basic knowledge of recruiting job seekers and beginners in the direction of C/C++ technology, in…
Efficient Architecture Search by Network Transformation, in AAAI 2018
2023年最新总结,阿里,腾讯,百度,美团,头条等技术面试题目,以及答案,专家出题人分析汇总。
PyTorch implementations of Generative Adversarial Networks.
aw_nas: A Modularized and Extensible NAS Framework
Models and examples built with TensorFlow
pathogen.vim: manage your runtimepath