mzq308734881 Goto Github PK

dukemtmc-videoreid

Instructions and baseline code for the DukeMTMC-VideoReID dataset

eccv2020-code

ECCV 2020 论文开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2020开源项目

ecn

Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification CVPR 2019

edu_vis

edu_vis教育信息可视化

education-visualization-competition

Tianchi visualizaiton competition

erasurehead

distributed gradient descent using approximate coding to mitigate stragglers

error-feedback-sgd

SGD with compressed gradients and error-feedback: https://arxiv.org/abs/1901.09847

face_recognition_framework

Multi-task face recognition framework based on PyTorch

fast-reid

SOTA ReID Methods and Toolbox

fastermoe

设计一个性能模型，在给定一个MoE模型和系统配置，性能模型可以准确地估计给定MoE模型与特定并行策略的性能（例如估计操作的延迟）

fedml

FedML - The federated learning and analytics library enabling secure and collaborative machine learning on decentralized data anywhere at any scale. Supporting large-scale cross-silo federated learning, cross-device federated learning on smartphones/IoTs, and research simulation. MLOps and App Marketplace are also enabled (https://open.fedml.ai).

firstvue

Vue入门

flashneuron

FlashNeuron是第一个使用 NVMe SSD 作为后备存储的 DNN 训练系统。为了充分利用有限的 SSD 写入带宽，FlashNeuron 引入了卸载调度程序，它可以在不增加 DNN 评估时间的情况下，选择性地将一组中间数据以压缩格式卸载到 SSD 中。 由于 GPU 和 SSD 直接通信以进行数据传输，因此 FlashNeuron 对 CPU 进程的干扰最小。

gaussiank-sgd

Understanding Top-k Sparsification in Distributed Deep Learning

grace

GRACE - GRAdient ComprEssion for distributed deep learning

gradient-compression

We present a set of all-reduce compatible gradient compression algorithms which significantly reduce the communication overhead while maintaining the performance of vanilla SGD. We empirically evaluate the performance of the compression methods by training deep neural networks on the CIFAR10 dataset.

gradient-quantization

vector quantization for stochastic gradient descent.

gtopkssgd

gTop-k S-SGD: A Communication-Efficient Distributed Synchronous SGD Algorithm for Deep Learning

hadoop

Apache Hadoop

handong1587.github.io

hicmd

[CVPR2020] Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification"

horovod

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

hydraplus-net

hypergraph_reid

inat_comp

iNaturalist competition details

incubator-echarts

A powerful, interactive charting and visualization library for browser

invoice

增值税发票OCR识别，使用flask微服务架构，识别type：增值税电子普通发票，增值税普通发票，增值税专用发票；识别字段为：发票代码、发票号码、开票日期、校验码、税后金额等

iocpserver

完成端口

javasocket

Socket通信

k-svd

K-SVD Methods for Image Denoising.