自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+
  • 博客(43)

原创 【Optimizor】Pytorch 实现汇总

Optimizor定义:fθf_\thetafθ​表示模型θt\theta_tθt​ 表示模型在更新t次后的参数y^=fθ(x)\hat{y} = f_\theta(x)y^​=fθ​(x) 表示模型预测值J(y^,y∗)J(\hat{y},y^*)J(y^​,y∗) 表示真值 y∗y^*y∗ 与预测值 y^\hat{y}y^​ 的损失函数∇J(θt)\nabla J\left(\t...

2020-05-06 15:46:29 89

原创 【Backbone】IBN-Net

IBN-NetTwo at Once: Enhancing Learning and Generalization Capacities via IBN-Nethttps://arxiv.org/abs/1807.09441Xingang Pan1, Ping Luo1, Jianping Shi2, and Xiaoou Tang1出自商汤, ECCV2018Question如何提高...

2020-05-03 15:24:13 124

原创 【Loss】Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
原力计划

Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticshttps://arxiv.org/abs/1705.07115CVPR 2018Alex Kendall University of CambridgeYarin Gal University of Oxford...

2020-04-30 23:57:51 360 2

原创 【ReID】首届“全国人工智能大赛”(行人重识别 Person ReID 赛项)

首届“全国人工智能大赛”(行人重识别 Person ReID 赛项

2020-04-15 00:27:05 842 1

原创 【Continual Learning】Encoder Based Lifelong Learning

Encoder Based Lifelong LearningICCV2017Amal Rannen Triki ∗† Rahaf Aljundi∗ Mathew B. Blaschko Tinne Tuytelaars KU LeuvenKU Leuven,ESAT-PSI, iMinds, BelgiumQuestionOur method aims at preserving...

2020-04-13 18:02:37 180

原创 【ReID】Strong Baseline

Bag of Tricks and A Strong Baseline for Deep Person Re-identificationHao LuoCVPR2019 OralQuestionHow to use some trick to improve the ability of re-id model and only use global features to achieve...

2020-04-08 21:01:35 335

原创 【Semantic Segmentation】语义分割综述 -- loss

【Semantic Segmentation】语义分割综述 -- losslossohemfocal-loss[Lovasz-Softmax loss] A tractable surrogate for the optimization of theintersection-over-union measure in neural networks (CVPR 2018)lossohemf...

2019-09-20 18:47:01 171

原创 【Semantic Segmentation】语义分割综述 -- 3D

【Semantic Segmentation】语义分割综述 -- 3D3D3D3D语义分割主要用于医学领域,包括3D造影分割检测病变体积,3D DNA分割得到氨基酸等。

2019-09-20 18:43:18 147

原创 【Semantic Segmentation】语义分割综述 -- NAS

【Semantic Segmentation】语义分割综述 -- NASNAS[Auto-DeepLab] Hierarchical Neural Architecture Search for Semantic Image Segmentation (CVPR2019)NAS[Auto-DeepLab] Hierarchical Neural Architecture Search for ...

2019-09-20 18:41:09 206

原创 【Semantic Segmentation】语义分割综述 - - Semi-supervised

【Semantic Segmentation】语义分割综述 - - Semi-supervisedSemi-supervisedWeakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features CVPR18Weakly-Supervised Semantic Segmentation Netwo...

2019-09-20 18:39:42 201

原创 【Semantic Segmentation】语义分割综述 -- Faster

【Semantic Segmentation】语义分割综述 -- FasterFaster[ESPNet] Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation 2018-03[Fast-SCNN] Fast Semantic Segmentation Network 2019-02[BiSeNet]...

2019-09-20 18:36:40 116 1

原创 【Semantic Segmentation】语义分割综述 -- Attention

【Semantic Segmentation】语义分割综述 -- AttentionAttention[Attention U-Net] Learning Where to Look for the Pancreas( MIDL 2018)[PAN] Pyramid Attention Network for Semantic Segmentation (BMVC 2018)[PSANet] Po...

2019-09-20 18:35:11 783

原创 【Semantic Segmentation】语义分割综述 -- Atrous Convolution

【Semantic Segmentation】语义分割综述 -- Atrous ConvolutionAtrous Convolution[DeepLabV2] Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,and Fully Connected CRFs 2016[ASPP] atrous...

2019-09-20 18:33:00 74

原创 【Semantic Segmentation】语义分割综述 -- Pyramid & Multi-Path

【Semantic Segmentation】语义分割综述 --- Pyramid & Multi-PathPyramid & Multi-Path[RefineNet] Multi-Path Refinement Networks for High-Resolution Semantic Segmentation 2016-11[PSPNet] Pyramid Scene Par...

2019-09-20 18:28:37 95

原创 【Semantic Segmentation】语义分割综述 -- Encoder And Decoder

【Semantic Segmentation】语义分割综述--Encoder And DecoderEncoder And Decoder[FCN] Fully Convolutional Networks for Semantic Segmentation 2016-05FCN-32FCN-16FCN-8code by pytorch[U-Net] Convolutional Networks...

2019-09-20 18:24:57 408

原创 【Object Detection】目标检测综述

目标检测论文介绍主要内容Deep Neural Networks for Object Detection论文介绍主要内容OverFeat,Integrated Recognition, Localization and Detection using Convolutional Networks.Rich feature hierarchies for accurate object detec...

2019-09-02 03:01:35 146

原创 【Semantic Segmentation】语义分割综述

【Semantic Segmentation】语言分割综述包括encoder decoder 结构空洞卷积注意力机制等在图像分割中的应用

2019-08-22 11:10:41 1529

原创 【Backbone】resNet

resnetDeep Residual Learning for Image Recognition (2015-12)https://arxiv.org/abs/1512.03385ResNet 最重要的贡献就是short cut,通过增加恒等映射,解决模型退化的问题。为什么可以解决模型退化问题呢?首先什么是模型退化问题,也就是加深简单的模型,不能直接提升模型的性能。我们在训练模...

2019-08-16 12:09:06 347

原创 【Attention】注意力机制在图像上的应用

【Attention】注意力机制在图像上的应用

2019-07-12 23:27:24 3183

原创 【Pose】Convolutional Pose Machines

【Pose】Convolutional Pose Machines3.1 Method3.2 Convolutional Pose Machines:3.2.1 Keypoint Localizaton Using Local Image Evidence3.2.2 Sequential Prediction with Learned Spatial Context Features算法流程使用阶...

2019-06-02 19:01:27 137

原创 微服务前后端分离角色权限认证体系

Spring Security:身份验证架构1.接收了Http请求2.根据用户凭据(credentials)创建AuthenticationToken3.为AuthenticationManagager委派创建的AuthenticationToken4.尝试以使用AuthenticationProvider列表进行身份验证5.UserDetailsS​​ervice是否必需?6. and 7. U...

2019-05-09 22:55:44 1523

原创 【软件测试】googleTest Clion win/ubuntu/mac cygwin测试环境搭建

googleTest Clion win/ubuntu cygwin测试环境搭建首先安装clion官网下载然后安装cygwin修改源为清华源:https://mirrors.tuna.tsinghua.edu.cn/help/cygwin/Cygwin 镜像使用帮助从 https://cygwin.com 上下载 setup-x86.exe 或 setup-x86_64.exe。选...

2019-04-23 01:10:22 229

原创 OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

2019-04-18 01:04:48 126

原创 Deep Neural Networks for Object Detection

Deep Neural Networks for Object Detection论文介绍1) 论文来源Szegedy C, Toshev A, Erhan D. Deep neural networks for object detection[C]//Advances in neural information processing systems. 2013: 2553-2561.2...

2019-04-17 01:23:11 251

原创 微服务后端框架安装

微服务后端框架安装dockerubuntu-docker最新版docker国内源设置mysqlRedisMongoDBelasticsearch创建实例并运行测试安装目录位置安装head插件rabbitmqdockerubuntu-docker最新版https://docs.docker.com/install/linux/docker-ce/ubuntu/docker国内源设置http...

2019-03-20 16:59:39 118

原创 李宏毅ML lecture-4,5 分类以及逻辑回归

李宏毅ML lecture-4,5 分类以及逻辑回归李宏毅ML lecture-6,7 Deep Learning李宏毅ML lecture-8,9 Keras 练习

2019-03-14 13:18:02 74

原创 李宏毅ML lecture-19 Transfer Learning

李宏毅ML lecture-17 Transfer LearningFine-tuningMultitask LearningDomain-adversarial trainingZero-shot LearingSelf-taught LearingSelf-taought Clustering迁移学习根据源数据以及目标数据是否被标注分为4大类。具体来讲,源数据指的是与当前任务无关的,或者关...

2019-03-12 18:12:17 80

原创 李宏毅ML lecture-17-18 unsupervised Learning Generation

李宏毅ML lecture-16 unsupervised Learning Generation

2019-03-09 14:40:48 160

原创 李宏毅ML lecture-16 unsupervised Learning Auto-encoder

李宏毅ML lecture-16 unsupervised Learning Auto-encoder

2019-03-05 14:48:35 136

原创 kaggle-组织病理学癌症检测

组织病理学癌症检测Histopathologic Cancer DetectionProject understanding比赛链接:https://www.kaggle.com/c/histopathologic-cancer-detection原文参考: https://www.kaggle.com/qitvision/a-complete-ml-pipeline-fast-ai识别从较...

2019-03-01 14:00:09 2200

原创 李宏毅ML lecture-15 unsupervised Learning Neighbor Embedding

李宏毅ML lecture-15 unsupervised Learning Neighbor EmbeddingManifold LearningLocally Linear Embedding (LLE)t-SNEManifold LearningLocally Linear Embedding (LLE)假设一个点可以由他周围的点线性组成...

2019-02-26 19:38:16 93

原创 Ubuntu下远程访问Jupyter Notebook 配置

Ubuntu下远程访问Jupyter Notebook 配置参考链接在windows上完全参考上面配置方式可用.但是Ubuntu18.04下会报错:Traceback (most recent call last): File "/home/arron/miniconda3/envs/machine/lib/python3.6/site-packages/notebook/notebo...

2019-02-25 12:11:37 396

原创 李宏毅ML lecture-13 unsupervised Learning Principle Component Analysis

李宏毅ML lecture-13 unsupervised Learning Principle Component Analysis聚类(Clustering)K-meansHAC数据降维(Dimension Reduction)PCA(Principal Component Analysis)基于特征值分解协方差矩阵实现PCA算法特征向量拉格朗日乘数法基于SVD分解协方差矩阵实现PCA算法PC...

2019-02-25 12:10:22 173

原创 李宏毅ML lecture-14 unsupervised Learning--Word Embeddng

李宏毅ML lecture-14 unsupervised Learning--Word Embeddng词嵌入(Word Embeddng),让计算机理解文章.实现方法有两种:https://nlp.stanford.edu/projects/glove/word vector paperTomas Mikolovhttps://blog.csdn.net/m0epnwsty...

2019-02-21 01:01:44 146

原创 李宏毅ML lecture-12 Semi-supervised Learning

李宏毅ML lecture-12 Semi-supervised Learning生成式模型EM算法参考判别式模型Low-density Separationself-trainingEntropy-based RegularizationSVM参考Smoothness AssumptionCluster and then LabelGraph-based ApproachBetter Repre...

2019-02-21 01:00:58 136

原创 李宏毅ML lecture-11 why deep

李宏毅ML lecture-11 why deepDeep → Modularization电路窗花End-to-end Learning使用Deep Learning 的理由learning more这节课主要将深度学习的深度是如何体现的.Seide, Frank, Gang Li, and Dong Yu. “Conversational Speech Transcription Usin...

2019-02-21 00:59:38 96

原创 李宏毅ML lecture-10 CNN

李宏毅ML lecture-10 CNNConvolutionstridepaddingMaxPoolingflattenFully Connected FeedforwardCNN的直观理解相关论文理解CNN深度强化网络CVAlexNetR-CNNNLP语言识别情感分析其他论文CNN比DNN更为简单CNN过滤器,目的就是寻找一种pattern,这种pattern远远小于整个图片的大小,同时是...

2019-02-21 00:58:55 128

原创 李宏毅ML lecture-1,2,3 线性回归及梯度下降

李宏毅ML lecture-2,3 线性回归及梯度下降 线性回归(Linear regression)损失函数( loss function)平方损失(square loss)学习率(Learning rate)momentumdecaynesterovRMSpropAdagradAdadeltaAdamAdamaxNadam偏执bias和方差variance正则化(regularization)...

2019-02-21 00:56:47 95

原创 李宏毅ML -lecture 0 机器学习介绍

李宏毅ML -lecture 0 机器学习介绍机器学习的领域如图所示,领域分为监督学习回归问题线性回归非线性回归深度学习SVMdecision treeK-NN分类问题逻辑回归半监督学习无监督学习聚类问题密度估计数据可视化强化学习迁移学习结构化学习未完待续…...

2019-02-21 00:54:37 109

原创 win10+ubuntu18.04双系统+cuda10+cudnn7.4+tensorRT5深度学习环境

win10+ubuntu18.04双系统+cuda10+cudnn7.4+tensorRT5深度学习环境一,首先下载ubuntu18.04。二,分区三,制作启动盘四,安装系统六,安装显卡驱动七,安装cuda八,安装cudnn九,安装tensorRT十,安装anaconda(python环境)十一,安装pycharm编辑器十二,安装python包创建python3.6虚拟环境激活环境安装tensor...

2019-02-21 00:52:55 1552

空空如也

空空如也

空空如也
提示
确定要删除当前文章?
取消 删除