pyjhzwh Goto Github PK

accelerate1rnn

use Eigen and SIMD to accelerate a simple 1-layer NN.

awesome-computer-vision

A curated list of awesome computer vision resources

awesome-point-cloud-analysis

A list of papers and datasets about point cloud analysis (processing)

blockdrop

BlockDrop: Dynamic Inference Paths in Residual Networks

caffe

Caffe: a fast open framework for deep learning.

caffe-wq

deepcompression-caffe-master

log quantization

deeplearning

Some practices about deep learning

df

The source code and dataset are used to demonstrate the DF model, and reproduce the results of the ACM CCS2018 paper

efficient-deep-learning-for-point-clouds

faiss

A library for efficient similarity search and clustering of dense vectors.

fedml

A Research-oriented Federated Learning Library. Supporting distributed computing, mobile/IoT on-device training, and standalone simulation. Best Paper Award at NeurIPS 2020 Federated Learning workshop. Join our Slack Community:(https://join.slack.com/t/fedml/shared_invite/zt-havwx1ee-a1xfOUrATNfc9DFqU~r34w)

floating-point-addition

使用Verilog设计的带四舍五入功能的浮点加法器

fpu

synthesiseable ieee 754 floating point library in verilog

grappolo

OpenMP implementation of Graph Community Detection, with a number of parallel heuristics/approximate computing techniques

hiddenlayer

Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.

hugo-academic

📝 The website builder for Hugo. Build and deploy a beautiful website in minutes!

impl-pruning-tf

Implementation of "Iterative pruning" on TensorFlow

incubator-tvm

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

inter-operator-scheduler

[MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration

llama

Inference code for LLaMA models

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

low-bit-quant-admm

admm for cnn layerwise weight low bit quantization

lq-net-pytorch

LQ-net implementation on pytorch

once-for-all

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

panyj-personal-website

places365

The Places365-CNNs for Scene Classification

pyjhzwh.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

pyreshark

A Wireshark plugin providing a simple interface for writing dissectors in Python.

qnnpack

Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators