HongjieLiu

darknet

Convolutional Neural Networks

JARVIS

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

LLaVA

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

vision

Datasets, Transforms and Models specific to Computer Vision

digital_video_introduction

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

tvm

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

lora

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

pytorch-cifar

95.47% on CIFAR10 with PyTorch

openh264

Open Source H.264 Codec

deep_sort

Simple Online Realtime Tracking with a Deep Association Metric

Luma3DS

Nintendo 3DS "Custom Firmware"

monodepth2

[ICCV 2019] Monocular depth estimation from a single image

g2o

g2o: A General Framework for Graph Optimization

ComputeLibrary

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

flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

YAD2K

YAD2K: Yet Another Darknet 2 Keras

xla

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

nnvm

cc

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

resnet-18-tensorflow

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

tvm-mali

Optimizing Mobile Deep Learning on ARM GPU with TVM

Model_zoo

Zhouyi model zoo

acoustic-interference-cancellation

acoustic interference (echo) cancellation project in summer internship

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)

ZipML-PYNQ

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

strassennets

Deep learning with a multiplication budget

backprop

Backpropagation in Python, C++, and Cuda

ZipML-XeonFPGA

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

blog_data

放一些博客需要用到的文件

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.