HongjieLiu

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Luma3DS

Nintendo 3DS "Custom Firmware"

DAMOV

DAMOV is a benchmark suite and a methodical framework targeting the study of data movement bottlenecks in modern applications. It is intended to study new architectures, such as near-data processing. Described by Oliveira et al. (preliminary version at https://arxiv.org/pdf/2105.03725.pdf)

xla

A machine learning compiler for GPUs, CPUs, and ML accelerators

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

backprop

Backpropagation in Python, C++, and Cuda

darknet

Convolutional Neural Networks

flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

Model_zoo

Zhouyi model zoo

g2o

g2o: A General Framework for Graph Optimization

blog_data

放一些博客需要用到的文件

acoustic-interference-cancellation

acoustic interference (echo) cancellation project in summer internship

openh264

Open Source H.264 Codec

digital_video_introduction

A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding). Translations: 🇺🇸 🇨🇳 🇯🇵 🇮🇹 🇰🇷 🇷🇺 🇧🇷 🇪🇸

cc

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

monodepth2

[ICCV 2019] Monocular depth estimation from a single image

deep_sort

Simple Online Realtime Tracking with a Deep Association Metric

vision

Datasets, Transforms and Models specific to Computer Vision

resnet-18-tensorflow

ResNet-18 TensorFlow Implementation including conversion of torch .t7 weights into tensorflow ckpt

redeye_sim

RedEye is a vision sensor designed to execute early stages of a deep convolutional neural network (ConvNet) in the analog domain. This repo is a modification of Caffe to train, simulate and visualize analog ConvNet processing under noise vs. energy tradeoffs.

ComputeLibrary

The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

nnvm

tvm-mali

Optimizing Mobile Deep Learning on ARM GPU with TVM

YAD2K

YAD2K: Yet Another Darknet 2 Keras

ZipML-PYNQ

Linear model training using stochastic gradient descent (SGD) on PYNQ with full to low precision.

ZipML-XeonFPGA

FPGA-based stochastic gradient descent (powered by ZipML - Low-precision machine learning on reconfigurable hardware)

strassennets

Deep learning with a multiplication budget

pytorch-cifar

95.47% on CIFAR10 with PyTorch