博客文章总目录-祥瑞的技术博客

港控/mmm° 2022-02-26 05:06 418阅读 0赞

直接点击标题进入文章。

[博客文章总目录-邢翔瑞的技术博客 ][-_]

博主github地址：[https://github.com/Xingxiangrui][https_github.com_Xingxiangrui]

邮件地址：1057945230@qq.com

每日任务繁忙，如果博主能够解答的问题乐意解答。但是如果问题博主不太了解或者太过细节复杂，恕不能详细解答和回复，见谅。

广告一波实验室：厦门大学智能数据分析与处理实验室

[https://xmu-smartdsp.github.io/introduction.html][https_xmu-smartdsp.github.io_introduction.html]

如果博文内容帮到你，欢迎打赏。

![2020011416502853.png][]![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl8zNjQ3NDgwOQ_size_16_color_FFFFFF_t_70][]

# 论文详解 #

###    图卷积网络GCN ###

[GCN (Graph Convolutional Network) 图卷积网络概览 ][GCN _Graph Convolutional Network_ _]

[图注意力网络(GAT) ICLR2018, Graph Attention Network论文详解 ][GAT_ ICLR2018_ Graph Attention Network_]

[旷视CVPR2019图卷积多标签图像识别Multi-Label Image Recognition with Graph Convolutional Networks论文详解 ][CVPR2019_Multi-Label Image Recognition with Graph Convolutional Networks_]

[无监督图嵌入Unsupervised graph embedding|基于对抗的图对齐adversarial graph alignment详解 ][Unsupervised graph embedding_adversarial graph alignment_]

###   图聚类Spectral clustering ###

[Graph特征提取方法:谱聚类(Spectral Clustering)详解 ][Graph_Spectral Clustering_]

###     GAN ###

[CycleGAN论文详解:Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks ][CycleGAN_Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks]

[pix2pix论文详解:Image-to-Image Translation with Conditional Adversarial Networks ][pix2pix_Image-to-Image Translation with Conditional Adversarial Networks]

###     图像分类 ###

[ILSVRC2017冠军SENet,Squeeze-and-Excitation Networks论文详解 ][ILSVRC2017_SENet_Squeeze-and-Excitation Networks_]

[YouTube-8M视频数据集概览 ][YouTube-8M_]

###     图像去噪 ###

[图像去噪论文Noise2Noise-Learning Image Restoration without Clean Data论文详解 ][Noise2Noise-Learning Image Restoration without Clean Data_]

###     目标检测 ###

[深度学习目标检测2013-2018模型总结概览及详解 ][2013-2018_]

[人脸检测算法MTCNN Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks论文详解 ][MTCNN Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks_]

###     机器学习 ###

[批归一化Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift论文详解 ][Batch Normalization_ Accelerating Deep Network Training by Reducing Internal Covariate Shift_]

[2018年11月12月机器学习相关文章概览 ][2018_11_12_]

[谷歌Nature论文alphaGo Zero: Mastering the game of Go without human knowledge论文详解 ][Nature_alphaGo Zero_ Mastering the game of Go without human knowledge_]

[谷歌论文Weight Agnostic Neural Networks（WANN）权重无关神经网络 ][Weight Agnostic Neural Networks_WANN_]

###     模型压缩 ###

[模型压缩经典论文SqueezeNet:AlexNet level accuracy with 50x fewer parameters and less 0.5MB model size论文详解 ][SqueezeNet_AlexNet level accuracy with 50x fewer parameters and less 0.5MB model size_]

[韩松Deep compression论文讲解——PPT加说明文字 ][Deep compression_PPT_]

[韩松DSD:Dense-sparse-dense training for deep neural networks论文详解 ][DSD_Dense-sparse-dense training for deep neural networks_]

[韩松EIE:Efficient Inference Engine on Compressed Deep Neural Network论文详解 ][EIE_Efficient Inference Engine on Compressed Deep Neural Network_]

[韩松博士毕业论文Efficient methods and hardware for deep learning论文详解 ][Efficient methods and hardware for deep learning_]

###     FPGA ###

[深鉴科技FPGA2017最佳论文ESE Efficient speech recognition engine with sparse LSTM on FPGA论文详解 ][FPGA2017_ESE Efficient speech recognition engine with sparse LSTM on FPGA_]

[PipeCNN论文详解：用OpenCL实现FPGA上的大型卷积网络加速 ][PipeCNN_OpenCL_FPGA_]

[韩松EIE:Efficient Inference Engine on Compressed Deep Neural Network论文详解 ][EIE_Efficient Inference Engine on Compressed Deep Neural Network_]

[韩松博士毕业论文Efficient methods and hardware for deep learning论文详解 ][Efficient methods and hardware for deep learning_]

# GNN图神经网络 #

###     GCN（Graph convolution Network）图卷积网络 ###

[GCN (Graph Convolutional Network) 图卷积网络概览 ][GCN _Graph Convolutional Network_ _]

[多标签图卷积分析项目与总结 ][Link 1]

[Graph Convolution Network图卷积网络（一）训练运行与代码概览 ][Graph Convolution Network_]

[Graph Convolution Network图卷积网络（二）数据加载与网络结构定义 ][Graph Convolution Network_ 1]

[Graph Convolution Network图卷积网络（三）嵌入其他网络结构 ][Graph Convolution Network_ 2]

###     GAT（Graph attention Network）图注意力网络 ###

[图注意力网络(GAT) ICLR2018, Graph Attention Network论文详解 ][GAT_ ICLR2018_ Graph Attention Network_]

[Graph Attention Network (一) 训练运行与代码概览 ][Graph Attention Network _ _]

[Graph Attention Network (二) 模型定义 ][Graph Attention Network _ _ 1]

[Graph Attention Network 图注意力网络 (三) 更改邻接masked attention ][Graph Attention Network _ _ _masked attention]

[GAT集群及服务器实验个人查阅汇总 ][GAT_]

###     ML-GCN（Multi-Label Graph Convolution Network） ###

[旷视CVPR2019图卷积多标签图像识别Multi-Label Image Recognition with Graph Convolutional Networks论文详解 ][CVPR2019_Multi-Label Image Recognition with Graph Convolutional Networks_]

[ML-GCN（一）代码训练与运行 ][ML-GCN_]

[ML-GCN（二）模型结构更改 ][ML-GCN_ 1]

###   图聚类Spectral clustering ###

[Graph特征提取方法:谱聚类(Spectral Clustering)详解 ][Graph_Spectral Clustering_]

[sklearn谱聚类Spectral Clustering(一)运行:以coco标签为例 ][sklearn_Spectral Clustering_coco_]

[sklearn谱聚类Spectral Clustering(二)参数及算法原理 ][sklearn_Spectral Clustering_]

# GAN对抗生成网络 #

[Text to image基于GAN的文本生成图像GAN-INT-CLS解析 ][Text to image_GAN_GAN-INT-CLS_]

##     cycleGAN ##

[CycleGAN论文详解:Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks ][CycleGAN_Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks]

[纺织品缺陷迁移项目实验及汇总 ][Link 2]

[光伏图像缺陷迁移项目实验及汇总 ][Link 3]

[缺陷迁移项目方法及思路以及结果测评 ][Link 4]

[CycleGAN（一）概览与运行 ][CycleGAN_]

[CycleGAN（二）数据集重做与训练测试 ][CycleGAN_ 1]

[CycleGAN（三）代码概览 ][CycleGAN_ 2]

[CycleGAN（四）inference过程与model定义 ][CycleGAN_inference_model_]

[CycleGAN（五）loss理解及更改与实验 ][CycleGAN_loss_]

[CycleGAN（六）模型结构更改 ][CycleGAN_ 3]

##     pix2pix ##

[pix2pix论文详解pix2pix:Image-to-Image Translation with Conditional Adversarial Networks ][pix2pix_Image-to-Image Translation with Conditional Adversarial Networks]

[pix2pix（一）制作样本对并进行训练与测试 ][pix2pix_]

[pix2pix（二）训练图像尺寸及分配显卡 ][pix2pix_ 1]

[纺织品缺陷迁移项目实验及汇总 ][Link 2]

##     分割 ##

[Unet论文详解U-Net:Convolutional Networks for Biomedical Image Segmentation ][Unet_U-Net_Convolutional Networks for Biomedical Image Segmentation]

[眼底血管分割MICCAI 2019论文详解Multi-task Neural Networks with Spatial Activation for Retinal Vessel... ][MICCAI 2019_Multi-task Neural Networks with Spatial Activation for Retinal Vessel...]

# 图像去噪 #

[图像去噪论文Noise2Noise-Learning Image Restoration without Clean Data论文详解 ][Noise2Noise-Learning Image Restoration without Clean Data_]

[NVlabs/noise2noise代码（一）概览与运行 ][NVlabs_noise2noise_]

[NVlabs/noise2noise代码（二）训练集的更改 ][NVlabs_noise2noise_ 1]

[NVlabs/noise2noise代码（三）网络训练代码解析 ][NVlabs_noise2noise_ 2]

# 多标签分类相关 #

[coco再分组与网络按照分组进行训练 ][coco_]

[输出多标签分类模型每class指标OP,OR,OF1,CP,CR,CF1 ][class_OP_OR_OF1_CP_CR_CF1]

[多标签分类模型验证结果badcase查找与存储 ][badcase_]

[COCO数据集标注框的读取及badcase analyse ][COCO_badcase analyse]

[多标签图卷积分析项目与总结 ][Link 1]

[2019.3-2019.6个人百度视觉技术部实习项目总结(缺陷迁移|多标签图卷积) ][2019.3-2019.6_]

[厦大研究生2019.3-6百度视觉技术部算法岗实习经历 ][2019.3-6_]

# 相关项目总结 #

[多标签图卷积分析项目与总结 ][Link 1]

[2019.3-2019.6个人百度视觉技术部实习项目总结(缺陷迁移|多标签图卷积) ][2019.3-2019.6_]

[厦大研究生2019.3-6百度视觉技术部算法岗实习经历 ][2019.3-6_]

[卡车玻璃后的人脸图像增强项目(框取|限制直方图|超分辨率重建) ][Link 5]

[2017.1-2018.4低运算复杂度和存储复杂度的图像分类网络实现 ][2017.1-2018.4_]

[2018.5-2019.1基于FPGA平台的目标检测网络实现 ][2018.5-2019.1_FPGA_]

[2017.1-2018.4基于迁移学习的水下图像分类 ][2017.1-2018.4_ 1]

[2016.12手机屏幕悬浮点检测 ][2016.12_]

# CV及机器学习 #

###     CV基础知识 ###

[CV基础问题(一)颜色空间|图像变换|摄像头 ][CV_]

###     机器学习基础知识 ###

[机器学习算法基础问题(一)PCA|SVM|贝叶斯|过拟合 ][PCA_SVM_]

[机器学习算法基础问题(二)类别不均|尺寸及感受野|Batch Norm|损失函数 ][Batch Norm_]

[深度学习概览及主流模型演进 ][Link 6]

# 目标检测 #

###     YOLO ###

[YOLO\_v1论文详解You Only Look Once,Unified, Real-Time Object Detection ][YOLO_v1_You Only Look Once_Unified_ Real-Time Object Detection]

[YOLO\_v2论文详解YOLO9000: Better, Faster, Stronge ][YOLO_v2_YOLO9000_ Better_ Faster_ Stronge]

[YOLOv3：Darknet代码解析（一）安装Darknet ][YOLOv3_Darknet_Darknet]

[YOLOv3：Darknet代码解析（二）代码初步 ][YOLOv3_Darknet_]

[YOLOv3：Darknet代码解析（三）卷积操作 ][YOLOv3_Darknet_ 1]

[YOLOv3：Darknet代码解析（四）结构更改与训练 ][YOLOv3_Darknet_ 2]

[YOLOv3：Darknet代码解析（五）权重与特征存储 ][YOLOv3_Darknet_ 3]

[YOLOv3：Darknet代码解析（六）简化的程序与卷积拆分 ][YOLOv3_Darknet_ 4]

###     MTCNN ###

[MTCNN（一）python代码训练与运行 ][MTCNN_python_]

[MTCNN（二）c代码概要 ][MTCNN_c_]

[MTCNN（三）基于python代码的网络结构更改 ][MTCNN_python_ 1]

[MTCNN（四）人头检测数据集参数调整 ][MTCNN_]

[MTCNN（五）c代码概览及权重的更改 ][MTCNN_c_ 1]

[MTCNN（六）c代码网络结构的更改 ][MTCNN_c_ 2]

[MTCNN（七）卷积更改为嵌套for循环格式 ][MTCNN_for_]

[MTCNN（八）openCV依赖库 ][MTCNN_openCV_]

[MTCNN（九）更改python与c代码的PReLU为ReLU ][MTCNN_python_c_PReLU_ReLU]

[MTCNN（十）输出python端权重到c端 ][MTCNN_python_c_]

[MTCNN的FPGA实现（一）SDK端程序的初步编写 ][MTCNN_FPGA_SDK_]

[c++编写神经网络（一）MTCNN内存空间的调用 ][c_MTCNN_]

[c++编写神经网络（二）MTCNN的程序主程序 ][c_MTCNN_ 1]

[FPGA实现MTCNN实现公交人头检测项目情况 ][FPGA_MTCNN_]

[zynq7020的ARM单片机编译与运行程序MTCNN ][zynq7020_ARM_MTCNN]

###     目标检测相关 ###

[目标检测网络mAP的测试的python实现 ][mAP_python_]

## 基础编程算法 ##

[基础编程汇总c++与python(一)数组|字符串|链表|递归 ][c_python_]

[内部排序算法归纳(算法原理|代码) ][Link 7]

# 数学相关 #

[概率相关实际问题汇总及解析 ][Link 8]

[比赛竞猜投注类问题概率模型 ][Link 9]

[王者荣耀中的数学原理及游戏策略(一)防御篇(护甲|魔抗|伤害运算机制) ][Link 10]

# C语言 #

[PCANet的c语言代码解析 ][PCANet_c_]

[数据流输入输出IPcore时c语言相关内容 ][IPcore_c_]

[DMA在linux下PS端c语言相关内容 ][DMA_linux_PS_c_]

[ARM用MIG调用DDR3的c程序解析 ][ARM_MIG_DDR3_c_]

[虚拟机交叉编译openCV详细步骤及bug解决详解 ][openCV_bug_]

[c++的namespace与class的相关知识 ][c_namespace_class_]

###     c++基础知识 ###

[c++基础知识汇总(一)ASICII码|存储|malloc与new|虚函数|类|静态变量|强制类型转换 ][c_ASICII_malloc_new_]

[c++基础知识汇总(三)计算机与编译原理 | static与const | 内联与虚函数 | sizeof ][c_ _ static_const _ _ _ sizeof]

[c++基础知识汇总(四) STL容器 | 类初始化| auto变量 ][c_ STL_ _ _ auto_]

###     c++实际应用编程汇总 ###

[c++实际应用编程汇总(一)堆与栈|位操作 ][c_]

[c++实际应用编程汇总(二)|字符串|数组|向量|输入输出 ][c_ 1]

###     基础算法 ###

[内部排序算法归纳(算法原理|代码) ][Link 7]

[c++链表问题汇总(代码及解析) ][c_ 2]

[c++策略类O(n)编程问题汇总(扑克的顺子|约瑟夫环|整数1出现的次数|股票最大利润) ][c_O_n_1_]

###     动态规划 ###

[c++动态规划类算法编程汇总(一)背包问题(可重复|不可重复)|回溯法 ][c_ 3]

[c++动态规划类算法编程汇总(二)全排列| O(n)排序 | manacher法 |滑窗|最长回文串 ][c_ O_n_ _ manacher_ _]

[c++动态规划类算法编程汇总(三)最长递增子序列|旅行家问题|拼为最小的数|丑数 ][c_ 4]

[c++动态规划类算法编程汇总(四)集合的子集|最长子序列(矩阵)的和(积) | 最大子矩阵 ][c_ _ _]

###     二叉树 ###

[二叉树原理及编程详解(一)完全二叉树|堆排序|遍历|重建 ][Link 11]

[二叉树原理及编程详解(二)红黑树|二叉搜索树 ][Link 12]

# 程序员养生指南 #

[端粒效应《The Telemere Effect》程序员的养生指南(一)压力、端粒与衰老 ][The Telemere Effect_]

[端粒效应《The Telemere Effect》程序员的养生指南(二)情绪、思维模式与健康 ][The Telemere Effect_ 1]

[端粒效应《The Telemere Effect》程序员的养生指南(三)身心与生活 ][The Telemere Effect_ 2]

# 计算机网络 #

[计算机网络基础(三次握手|TCP/IP协议|五层协议栈|网络安全) ][TCP_IP_]

# SQL数据库 #

[SQL基础(定义|基本语句|基本函数) ][SQL_]

# Python及深度学习框架 #

##   python ##

[macOS上运行python及配置相应环境 ][macOS_python_]

[python应用实例(一)常见运算|维度|基本元素|基本语法|函数 ][python_]

[python应用实例(二)制作数据集相关: label更改与批量化图片处理 ][python_ label_]

[python应用实例(三)数据聚类相关|迭代分组|子矩阵|字典映射|遍历 ][python_ 1]

[python应用实例(四)用pandas将结果写入html表格之中 ][python_pandas_html_]

[python项目应用实例(五)生成图像heatmap|数据降维PCA|数据可视化|图像格式转换 ][python_heatmap_PCA_]

[python项目应用实例(六)输入输出|递归|深浅拷贝|全局变量|复数 ][python_ 2]

##   TensorFlow ##

[Tensorflow相关知识（一）MTCNN代码相关 ][Tensorflow_MTCNN_]

[Tensorflow相关知识（二）运用loss及gradients更新variables ][Tensorflow_loss_gradients_variables]

##   PyTorch ##

[PyTorch应用实例(一)加载(本地|官方)预训练模型 ][PyTorch_]

[PyTorch应用实例(二)ResNet | SENet实现coco多标签分类 ][PyTorch_ResNet _ SENet_coco_]

[PyTorch应用实例(三)通用的图像分类模型实现图像分类(附代码与操作方法) ][PyTorch_ 1]

[PyTorch应用实例(四)设置learning\_rate的decay ][PyTorch_learning_rate_decay]

[PyTorch应用实例(五)加载模型验证并将所有结果写入文件 ][PyTorch_ 2]

[PyTorch应用实例(六)并行化|分组运算|张量乘|常用神经网络层 ][PyTorch_ 3]

[PyTorch应用实例(七)模型添加中继loss | 中继监督优化 ][PyTorch_loss _ _]

[PyTorch应用实例(八)固定权重|顺序训练网络 ][PyTorch_ 4]

# Linux及环境配置 #

[常用Linux指令汇总 ][Linux_]

[Linux中显卡用户管理相关应用及命令行 ][Linux_ 1]

[macOS上运行python及配置相应环境 ][macOS_python_]

[macOS上用PyCharm本地配置Anaconda环境 ][macOS_PyCharm_Anaconda_]

[客户端配置Hadoop并运用SLURM GPU集群与HDFS文件系统 ][Hadoop_SLURM GPU_HDFS_]

[linux操作系统基础知识 ][linux_]

###    SSH相关 ###

[windows PC用SSH连接Ubuntu14.04的配置与方法 ][windows PC_SSH_Ubuntu14.04_]

[macOS与CentOS之间互传文件(iTerm2与lrzsz) ][macOS_CentOS_iTerm2_lrzsz_]

[macOS系统用SSH链接CentOS服务器 ][macOS_SSH_CentOS_]

###    环境配置相关 ###

[在CentOS 6.3上配置PyTorch与gcc ][CentOS 6.3_PyTorch_gcc]

[CentOS 6.3安装anaconda并配置pytorch与cuda ][CentOS 6.3_anaconda_pytorch_cuda]

[Ubuntu14.04安装Anaconda3-2018.12-x86\_64 ][Ubuntu14.04_Anaconda3-2018.12-x86_64]

[运用Anaconda对python 3.6与tensorflow-gpu与pip环境配置 ][Anaconda_python 3.6_tensorflow-gpu_pip_]

[虚拟环境中用Anaconda安装显卡CUDA驱动与CUDA运行版本匹配 ][Anaconda_CUDA_CUDA_]

[虚拟机上安装openCV ][openCV]

[macbook操作与快捷键个人查阅汇总 ][macbook_]

[docker安装及环境容器上传 ][docker_]

###    github相关 ###

[运用github管理项目不同平台之间互传文件 ][github_]

###    GPU集群相关 ###

[客户端配置并运用SLURM GPU集群 ][Hadoop_SLURM GPU_HDFS_]

[GAT集群及服务器实验个人查阅汇总 ][GAT_]

###     机器学习相关 ###

[运用百度智能云进行简单图像分类 ][Link 13]

# FPGA #

###    FPGA基础知识 ###

[FPGA基础知识（一）UG998相关硬件知识 ][FPGA_UG998_]

[FPGA基础知识（二）HLS相关知识 ][FPGA_HLS_]

[FPGA基础知识（三）UG902 接口综合 ][FPGA_UG902 _]

[FPGA基础知识（四）UG902 RTL simulation and export ][FPGA_UG902 RTL simulation and export]

[FPGA基础知识（五）系统集成知识 ][FPGA_]

[FPGA基础知识（六）UG586 Mermoy Interface Solutions ][FPGA_UG586 Mermoy Interface Solutions]

[FPGA基础知识（七）片上单片机 ][FPGA_ 1]

[FPGA基础知识（八）vivado设计流程中的知识 ][FPGA_vivado_]

[FPGA基础知识（九）SDK相关知识 ][FPGA_SDK_]

[FPGA基础知识（十）DMA与AXI4总线 ][FPGA_DMA_AXI4_]

[尝试用IPcore调用DDR3及相关知识 ][IPcore_DDR3_]

###    vivado HLS硬件化指令 ###

[vivado HLS硬件化指令（一）HLS针对循环的硬件优化 ][vivado HLS_HLS_]

[vivado HLS硬件化指令（二）HLS针对数组的硬件优化 ][vivado HLS_HLS_ 1]

[vivado HLS硬件化指令（三）HLS增大运算吞吐量的硬件优化 ][vivado HLS_HLS_ 2]

[vivado HLS硬件化指令（四）卷积相关的指令优化 ][vivado HLS_]

[卷积操作的HLS优化 ][HLS_]

###    FPGA实践教程 ###

[FPGA实践教程（一）用HLS将c程序生成IPcore ][FPGA_HLS_c_IPcore]

[FPGA实践教程（二）连接片上ARM ][FPGA_ARM]

[FPGA实践教程（三）系统搭建与烧录 ][FPGA_ 2]

[FPGA实践教程（四）片上ARM运行程序 ][FPGA_ARM_]

[FPGA实践教程（五）PS用MIG调用DDR ][FPGA_PS_MIG_DDR]

[FPGA实践教程（六）AXI-Lite实现PS与PL通信 ][FPGA_AXI-Lite_PS_PL_]

[FPGA实践教程（八）PS与PL共享DDR ][FPGA_PS_PL_DDR]

[FPGA vivado系统集成操作 ][FPGA vivado_]

[DMA在linux下PS端c语言相关内容 ][DMA_linux_PS_c_]

[数据流输入输出IPcore时c语言相关内容 ][IPcore_c_]

[调通DMA系统集成中遇到的问题 ][DMA_]

[ARM用MIG调用DDR3的c程序解析 ][ARM_MIG_DDR3_c_]

[MIZ7035上的AXI接口的MIG测试 ][MIZ7035_AXI_MIG_]

[MIZ7035交叉编译单片机程序运行 ][MIZ7035_]

###    zynqNet ###

[ZynqNet解析（一）概览 ][ZynqNet_]

[ZynqNet解析（二）运行与调试 ][ZynqNet_ 1]

[ZynqNet解析（三）CPU端程序解析 ][ZynqNet_CPU_]

[ZynqNet解析（四）FPGA端程序解析 ][ZynqNet_FPGA_]

[ZynqNet解析（五）具体硬件实现 ][ZynqNet_ 2]

[ZynqNet解析（六）内存的实现 ][ZynqNet_ 3]

[ZynqNet解析（七）实现于BRAM上的Cache ][ZynqNet_BRAM_Cache]

[ZynqNet解析（八）对IPcore的HLS ][ZynqNet_IPcore_HLS]

###    卷积的FPGA实现 ###

[卷积函数的FPGA实现（一）编写卷积IPcore的BRAM实现 ][FPGA_IPcore_BRAM_]

[卷积函数的FPGA实现（二）卷积的相乘累加单元的实现 ][FPGA_ 3]

[卷积函数的FPGA实现（三）加入HLS预编译指令 ][FPGA_HLS_ 1]

[卷积函数的FPGA实现（四）函数接口的HLS ][FPGA_HLS]

[卷积函数的FPGA实现（五）对IPcore进行HLS及bug查找 ][FPGA_IPcore_HLS_bug_]

[卷积函数的FPGA实现（六）对IPcore进行HLS及RTL输出 ][FPGA_IPcore_HLS_RTL_]

[卷积函数的FPGA实现（七）vivado系统集成与烧录 ][FPGA_vivado_ 1]

[卷积函数的FPGA实现（八）IPcore的BRAM尺寸及加入偏置和ReLU ][FPGA_IPcore_BRAM_ReLU]

[卷积函数的FPGA实现（九）WBRAM的重新实现 ][FPGA_WBRAM_]

[MTCNN的FPGA实现（一）SDK端程序的初步编写 ][MTCNN_FPGA_SDK_]

[卷积IPcore详细报告及进展 ][IPcore_]

# 硬件 #

##    嵌入式 ##

[虚拟机交叉编译openCV详细步骤及bug解决详解 ][openCV_bug_]

[zynq7020的ARM单片机编译与运行程序MTCNN ][zynq7020_ARM_MTCNN]

[嵌入式：编译程序并传至Hi3516运行 ][Hi3516_]

[FPGA片上PS在SDK编译环境下调用DMA ][FPGA_PS_SDK_DMA]

[ARM用MIG调用DDR3的c程序解析 ][ARM_MIG_DDR3_c_]

[FPGA基础知识（七）片上单片机 ][FPGA_ 1]

[虚拟机上安装openCV ][openCV]

[MIZ7035交叉编译单片机程序运行 ][MIZ7035_]

###    硬件平台 ###

[Xilinx zynq系列FPGA实现神经网络中相关资源评估 ][Xilinx zynq_FPGA_]

[在zynq平台实现目标检测网络项目汇报与交接 ][zynq_]

[FLOPS与GOPS：各平台及神经网络算力算量调研 ][FLOPS_GOPS_]

[深鉴科技DNNDK概览 ][DNNDK_]

[虚拟机上安装openCV ][openCV]

[-_]: https://blog.csdn.net/weixin_36474809/article/details/88884137
[https_github.com_Xingxiangrui]: https://github.com/Xingxiangrui
[https_xmu-smartdsp.github.io_introduction.html]: https://xmu-smartdsp.github.io/introduction.html
[2020011416502853.png]: https://img-blog.csdnimg.cn/2020011416502853.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl8zNjQ3NDgwOQ_size_16_color_FFFFFF_t_70]: /images/20220226/98eb5ca26c8a4221a5573239714bde24.png
[GCN _Graph Convolutional Network_ _]: https://blog.csdn.net/weixin_36474809/article/details/89316439
[GAT_ ICLR2018_ Graph Attention Network_]: https://blog.csdn.net/weixin_36474809/article/details/89401552
[CVPR2019_Multi-Label Image Recognition with Graph Convolutional Networks_]: https://blog.csdn.net/weixin_36474809/article/details/89450262
[Unsupervised graph embedding_adversarial graph alignment_]: https://blog.csdn.net/weixin_36474809/article/details/93882645
[Graph_Spectral Clustering_]: https://blog.csdn.net/weixin_36474809/article/details/89669623
[CycleGAN_Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks]: https://blog.csdn.net/weixin_36474809/article/details/88778213
[pix2pix_Image-to-Image Translation with Conditional Adversarial Networks]: https://blog.csdn.net/weixin_36474809/article/details/89004841
[ILSVRC2017_SENet_Squeeze-and-Excitation Networks_]: https://blog.csdn.net/weixin_36474809/article/details/90517954
[YouTube-8M_]: https://blog.csdn.net/weixin_36474809/article/details/91356579
[Noise2Noise-Learning Image Restoration without Clean Data_]: https://blog.csdn.net/weixin_36474809/article/details/86535639
[2013-2018_]: https://blog.csdn.net/weixin_36474809/article/details/84172579
[MTCNN Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks_]: https://blog.csdn.net/weixin_36474809/article/details/86239317
[Batch Normalization_ Accelerating Deep Network Training by Reducing Internal Covariate Shift_]: https://blog.csdn.net/weixin_36474809/article/details/86699765
[2018_11_12_]: https://blog.csdn.net/weixin_36474809/article/details/85916894
[Nature_alphaGo Zero_ Mastering the game of Go without human knowledge_]: https://blog.csdn.net/weixin_36474809/article/details/86172679
[Weight Agnostic Neural Networks_WANN_]: https://blog.csdn.net/weixin_36474809/article/details/103368471
[SqueezeNet_AlexNet level accuracy with 50x fewer parameters and less 0.5MB model size_]: https://blog.csdn.net/weixin_36474809/article/details/85788474
[Deep compression_PPT_]: https://blog.csdn.net/weixin_36474809/article/details/80643784
[DSD_Dense-sparse-dense training for deep neural networks_]: https://blog.csdn.net/weixin_36474809/article/details/85322584
[EIE_Efficient Inference Engine on Compressed Deep Neural Network_]: https://blog.csdn.net/weixin_36474809/article/details/85326634
[Efficient methods and hardware for deep learning_]: https://blog.csdn.net/weixin_36474809/article/details/85613013
[FPGA2017_ESE Efficient speech recognition engine with sparse LSTM on FPGA_]: https://blog.csdn.net/weixin_36474809/article/details/86079131
[PipeCNN_OpenCL_FPGA_]: https://blog.csdn.net/weixin_36474809/article/details/80900197
[Link 1]: https://blog.csdn.net/weixin_36474809/article/details/92774264
[Graph Convolution Network_]: https://blog.csdn.net/weixin_36474809/article/details/89373123
[Graph Convolution Network_ 1]: https://blog.csdn.net/weixin_36474809/article/details/89379727
[Graph Convolution Network_ 2]: https://blog.csdn.net/weixin_36474809/article/details/90704872
[Graph Attention Network _ _]: https://blog.csdn.net/weixin_36474809/article/details/89350573
[Graph Attention Network _ _ 1]: https://blog.csdn.net/weixin_36474809/article/details/89447533
[Graph Attention Network _ _ _masked attention]: https://blog.csdn.net/weixin_36474809/article/details/90693821
[GAT_]: https://blog.csdn.net/weixin_36474809/article/details/90633638
[ML-GCN_]: https://blog.csdn.net/weixin_36474809/article/details/89466776
[ML-GCN_ 1]: https://blog.csdn.net/weixin_36474809/article/details/89501480
[sklearn_Spectral Clustering_coco_]: https://blog.csdn.net/weixin_36474809/article/details/89855869
[sklearn_Spectral Clustering_]: https://blog.csdn.net/weixin_36474809/article/details/89927502
[Text to image_GAN_GAN-INT-CLS_]: https://blog.csdn.net/weixin_36474809/article/details/102997864
[Link 2]: https://blog.csdn.net/weixin_36474809/article/details/88786116
[Link 3]: https://blog.csdn.net/weixin_36474809/article/details/89184538
[Link 4]: https://blog.csdn.net/weixin_36474809/article/details/89670625
[CycleGAN_]: https://blog.csdn.net/weixin_36474809/article/details/88734546
[CycleGAN_ 1]: https://blog.csdn.net/weixin_36474809/article/details/88744763
[CycleGAN_ 2]: https://blog.csdn.net/weixin_36474809/article/details/88823295
[CycleGAN_inference_model_]: https://blog.csdn.net/weixin_36474809/article/details/88863829
[CycleGAN_loss_]: https://blog.csdn.net/weixin_36474809/article/details/88895136
[CycleGAN_ 3]: https://blog.csdn.net/weixin_36474809/article/details/88949462
[pix2pix_]: https://blog.csdn.net/weixin_36474809/article/details/89004591
[pix2pix_ 1]: https://blog.csdn.net/weixin_36474809/article/details/89192677
[Unet_U-Net_Convolutional Networks for Biomedical Image Segmentation]: https://blog.csdn.net/weixin_36474809/article/details/87931260
[MICCAI 2019_Multi-task Neural Networks with Spatial Activation for Retinal Vessel...]: https://blog.csdn.net/weixin_36474809/article/details/102854635
[NVlabs_noise2noise_]: https://blog.csdn.net/weixin_36474809/article/details/86600925
[NVlabs_noise2noise_ 1]: https://blog.csdn.net/weixin_36474809/article/details/86612597
[NVlabs_noise2noise_ 2]: https://blog.csdn.net/weixin_36474809/article/details/87919252
[coco_]: https://blog.csdn.net/weixin_36474809/article/details/90169078
[class_OP_OR_OF1_CP_CR_CF1]: https://blog.csdn.net/weixin_36474809/article/details/90231745
[badcase_]: https://blog.csdn.net/weixin_36474809/article/details/90240425
[COCO_badcase analyse]: https://blog.csdn.net/weixin_36474809/article/details/90262591
[2019.3-2019.6_]: https://blog.csdn.net/weixin_36474809/article/details/92816375
[2019.3-6_]: https://blog.csdn.net/weixin_36474809/article/details/88556862
[Link 5]: https://blog.csdn.net/weixin_36474809/article/details/94601863
[2017.1-2018.4_]: https://blog.csdn.net/weixin_36474809/article/details/97273981
[2018.5-2019.1_FPGA_]: https://blog.csdn.net/weixin_36474809/article/details/97104877
[2017.1-2018.4_ 1]: https://blog.csdn.net/weixin_36474809/article/details/98497187
[2016.12_]: https://blog.csdn.net/weixin_36474809/article/details/99656161
[CV_]: https://blog.csdn.net/weixin_36474809/article/details/90752050
[PCA_SVM_]: https://blog.csdn.net/weixin_36474809/article/details/90753252
[Batch Norm_]: https://blog.csdn.net/weixin_36474809/article/details/98597337
[Link 6]: https://blog.csdn.net/weixin_36474809/article/details/100534384
[YOLO_v1_You Only Look Once_Unified_ Real-Time Object Detection]: https://blog.csdn.net/weixin_36474809/article/details/101621236
[YOLO_v2_YOLO9000_ Better_ Faster_ Stronge]: https://blog.csdn.net/weixin_36474809/article/details/101868628
[YOLOv3_Darknet_Darknet]: https://blog.csdn.net/weixin_36474809/article/details/80881043
[YOLOv3_Darknet_]: https://blog.csdn.net/weixin_36474809/article/details/80975845
[YOLOv3_Darknet_ 1]: https://blog.csdn.net/weixin_36474809/article/details/81296612
[YOLOv3_Darknet_ 2]: https://blog.csdn.net/weixin_36474809/article/details/81326286
[YOLOv3_Darknet_ 3]: https://blog.csdn.net/weixin_36474809/article/details/81331175
[YOLOv3_Darknet_ 4]: https://blog.csdn.net/weixin_36474809/article/details/81739771
[MTCNN_python_]: https://blog.csdn.net/weixin_36474809/article/details/82752199
[MTCNN_c_]: https://blog.csdn.net/weixin_36474809/article/details/82839157
[MTCNN_python_ 1]: https://blog.csdn.net/weixin_36474809/article/details/82856171
[MTCNN_]: https://blog.csdn.net/weixin_36474809/article/details/82892682
[MTCNN_c_ 1]: https://blog.csdn.net/weixin_36474809/article/details/82991552
[MTCNN_c_ 2]: https://blog.csdn.net/weixin_36474809/article/details/83056795
[MTCNN_for_]: https://blog.csdn.net/weixin_36474809/article/details/83145601
[MTCNN_openCV_]: https://blog.csdn.net/weixin_36474809/article/details/83343514
[MTCNN_python_c_PReLU_ReLU]: https://blog.csdn.net/weixin_36474809/article/details/84578946
[MTCNN_python_c_]: https://blog.csdn.net/weixin_36474809/article/details/84789385
[MTCNN_FPGA_SDK_]: https://blog.csdn.net/weixin_36474809/article/details/85091609
[c_MTCNN_]: https://blog.csdn.net/weixin_36474809/article/details/85990687
[c_MTCNN_ 1]: https://blog.csdn.net/weixin_36474809/article/details/86061262
[FPGA_MTCNN_]: https://blog.csdn.net/weixin_36474809/article/details/83305490
[zynq7020_ARM_MTCNN]: https://blog.csdn.net/weixin_36474809/article/details/83342549
[mAP_python_]: https://blog.csdn.net/weixin_36474809/article/details/86517885
[c_python_]: https://blog.csdn.net/weixin_36474809/article/details/90924100
[Link 7]: https://blog.csdn.net/weixin_36474809/article/details/94579590
[Link 8]: https://blog.csdn.net/weixin_36474809/article/details/101448598
[Link 9]: https://blog.csdn.net/weixin_36474809/article/details/102842063
[Link 10]: https://blog.csdn.net/weixin_36474809/article/details/102087639
[PCANet_c_]: https://blog.csdn.net/weixin_36474809/article/details/80846281
[IPcore_c_]: https://blog.csdn.net/weixin_36474809/article/details/80816091
[DMA_linux_PS_c_]: https://blog.csdn.net/weixin_36474809/article/details/80761831
[ARM_MIG_DDR3_c_]: https://blog.csdn.net/weixin_36474809/article/details/81012267
[openCV_bug_]: https://blog.csdn.net/weixin_36474809/article/details/83501207
[c_namespace_class_]: https://blog.csdn.net/weixin_36474809/article/details/83308733
[c_ASICII_malloc_new_]: https://blog.csdn.net/weixin_36474809/article/details/90749387
[c_ vector _ size _ _]: https://blog.csdn.net/weixin_36474809/article/details/85125489
[c_ _ static_const _ _ _ sizeof]: https://blog.csdn.net/weixin_36474809/article/details/100535653
[c_ STL_ _ _ auto_]: https://blog.csdn.net/weixin_36474809/article/details/100053957
[c_]: https://blog.csdn.net/weixin_36474809/article/details/91347601
[c_ 1]: https://blog.csdn.net/weixin_36474809/article/details/97613215
[c_ 2]: https://blog.csdn.net/weixin_36474809/article/details/100186779
[c_O_n_1_]: https://blog.csdn.net/weixin_36474809/article/details/100170310
[c_ 3]: https://blog.csdn.net/weixin_36474809/article/details/97000362
[c_ O_n_ _ manacher_ _]: https://blog.csdn.net/weixin_36474809/article/details/100044593
[c_ 4]: https://blog.csdn.net/weixin_36474809/article/details/100401576
[c_ _ _]: https://blog.csdn.net/weixin_36474809/article/details/100581124
[Link 11]: https://blog.csdn.net/weixin_36474809/article/details/97528452
[Link 12]: https://blog.csdn.net/weixin_36474809/article/details/98471216
[The Telemere Effect_]: https://blog.csdn.net/weixin_36474809/article/details/102511466
[The Telemere Effect_ 1]: https://blog.csdn.net/weixin_36474809/article/details/102521826
[The Telemere Effect_ 2]: https://blog.csdn.net/weixin_36474809/article/details/102550942
[TCP_IP_]: https://blog.csdn.net/weixin_36474809/article/details/97539457
[SQL_]: https://blog.csdn.net/weixin_36474809/article/details/99697651
[macOS_python_]: https://blog.csdn.net/weixin_36474809/article/details/89095425
[python_]: https://blog.csdn.net/weixin_36474809/article/details/88101294
[python_ label_]: https://blog.csdn.net/weixin_36474809/article/details/89109823
[python_ 1]: https://blog.csdn.net/weixin_36474809/article/details/89915754
[python_pandas_html_]: https://blog.csdn.net/weixin_36474809/article/details/90259445
[python_heatmap_PCA_]: https://blog.csdn.net/weixin_36474809/article/details/90370876
[python_ 2]: https://blog.csdn.net/weixin_36474809/article/details/90758145
[Tensorflow_MTCNN_]: https://blog.csdn.net/weixin_36474809/article/details/83116838
[Tensorflow_loss_gradients_variables]: https://blog.csdn.net/weixin_36474809/article/details/88031720
[PyTorch_]: https://blog.csdn.net/weixin_36474809/article/details/89646008
[PyTorch_ResNet _ SENet_coco_]: https://blog.csdn.net/weixin_36474809/article/details/89715056
[PyTorch_ 1]: https://blog.csdn.net/weixin_36474809/article/details/90030682
[PyTorch_learning_rate_decay]: https://blog.csdn.net/weixin_36474809/article/details/90083434
[PyTorch_ 2]: https://blog.csdn.net/weixin_36474809/article/details/90207499
[PyTorch_ 3]: https://blog.csdn.net/weixin_36474809/article/details/90376883
[PyTorch_loss _ _]: https://blog.csdn.net/weixin_36474809/article/details/90443396
[PyTorch_ 4]: https://blog.csdn.net/weixin_36474809/article/details/90511393
[Linux_]: https://blog.csdn.net/weixin_36474809/article/details/82588543
[Linux_ 1]: https://blog.csdn.net/weixin_36474809/article/details/89637261
[macOS_PyCharm_Anaconda_]: https://blog.csdn.net/weixin_36474809/article/details/90299833
[Hadoop_SLURM GPU_HDFS_]: https://blog.csdn.net/weixin_36474809/article/details/89467933
[linux_]: https://blog.csdn.net/weixin_36474809/article/details/103528951
[windows PC_SSH_Ubuntu14.04_]: https://blog.csdn.net/weixin_36474809/article/details/86604468
[macOS_CentOS_iTerm2_lrzsz_]: https://blog.csdn.net/weixin_36474809/article/details/88748878
[macOS_SSH_CentOS_]: https://blog.csdn.net/weixin_36474809/article/details/88710505
[CentOS 6.3_PyTorch_gcc]: https://blog.csdn.net/weixin_36474809/article/details/88715360
[CentOS 6.3_anaconda_pytorch_cuda]: https://blog.csdn.net/weixin_36474809/article/details/88799164
[Ubuntu14.04_Anaconda3-2018.12-x86_64]: https://blog.csdn.net/weixin_36474809/article/details/87804903
[Anaconda_python 3.6_tensorflow-gpu_pip_]: https://blog.csdn.net/weixin_36474809/article/details/87714182
[Anaconda_CUDA_CUDA_]: https://blog.csdn.net/weixin_36474809/article/details/87820314
[openCV]: https://blog.csdn.net/weixin_36474809/article/details/83373908
[macbook_]: https://blog.csdn.net/weixin_36474809/article/details/88714642
[docker_]: https://blog.csdn.net/weixin_36474809/article/details/89518185
[github_]: https://blog.csdn.net/weixin_36474809/article/details/89013772
[Link 13]: https://blog.csdn.net/weixin_36474809/article/details/89358435
[FPGA_UG998_]: https://blog.csdn.net/weixin_36474809/article/details/80593922
[FPGA_HLS_]: https://blog.csdn.net/weixin_36474809/article/details/80594481
[FPGA_UG902 _]: https://blog.csdn.net/weixin_36474809/article/details/80600842
[FPGA_UG902 RTL simulation and export]: https://blog.csdn.net/weixin_36474809/article/details/80610689
[FPGA_]: https://blog.csdn.net/weixin_36474809/article/details/80673673
[FPGA_UG586 Mermoy Interface Solutions]: https://blog.csdn.net/weixin_36474809/article/details/80985040
[FPGA_ 1]: https://blog.csdn.net/weixin_36474809/article/details/81164329
[FPGA_vivado_]: https://blog.csdn.net/weixin_36474809/article/details/81170725
[FPGA_SDK_]: https://blog.csdn.net/weixin_36474809/article/details/81180514
[FPGA_DMA_AXI4_]: https://blog.csdn.net/weixin_36474809/article/details/81009769
[IPcore_DDR3_]: https://blog.csdn.net/weixin_36474809/article/details/81018040
[vivado HLS_HLS_]: https://blog.csdn.net/weixin_36474809/article/details/81479551
[vivado HLS_HLS_ 1]: https://blog.csdn.net/weixin_36474809/article/details/81483993
[vivado HLS_HLS_ 2]: https://blog.csdn.net/weixin_36474809/article/details/81665911
[vivado HLS_]: https://blog.csdn.net/weixin_36474809/article/details/84587535
[HLS_]: https://blog.csdn.net/weixin_36474809/article/details/81504665
[FPGA_HLS_c_IPcore]: https://blog.csdn.net/weixin_36474809/article/details/80597166
[FPGA_ARM]: https://blog.csdn.net/weixin_36474809/article/details/80691642
[FPGA_ 2]: https://blog.csdn.net/weixin_36474809/article/details/80840448
[FPGA_ARM_]: https://blog.csdn.net/weixin_36474809/article/details/80743037
[FPGA_PS_MIG_DDR]: https://blog.csdn.net/weixin_36474809/article/details/80997945
[FPGA_AXI-Lite_PS_PL_]: https://blog.csdn.net/weixin_36474809/article/details/81206660
[FPGA_PS_PL_DDR]: https://blog.csdn.net/weixin_36474809/article/details/85111550
[FPGA vivado_]: https://blog.csdn.net/weixin_36474809/article/details/80690368
[DMA_]: https://blog.csdn.net/weixin_36474809/article/details/80830229
[MIZ7035_AXI_MIG_]: https://blog.csdn.net/weixin_36474809/article/details/86594205
[MIZ7035_]: https://blog.csdn.net/weixin_36474809/article/details/86487043
[ZynqNet_]: https://blog.csdn.net/weixin_36474809/article/details/82621009
[ZynqNet_ 1]: https://blog.csdn.net/weixin_36474809/article/details/82631055
[ZynqNet_CPU_]: https://blog.csdn.net/weixin_36474809/article/details/82663929
[ZynqNet_FPGA_]: https://blog.csdn.net/weixin_36474809/article/details/82683399
[ZynqNet_ 2]: https://blog.csdn.net/weixin_36474809/article/details/82702008
[ZynqNet_ 3]: https://blog.csdn.net/weixin_36474809/article/details/83409853
[ZynqNet_BRAM_Cache]: https://blog.csdn.net/weixin_36474809/article/details/83860624
[ZynqNet_IPcore_HLS]: https://blog.csdn.net/weixin_36474809/article/details/84969403
[FPGA_IPcore_BRAM_]: https://blog.csdn.net/weixin_36474809/article/details/83658473
[FPGA_ 3]: https://blog.csdn.net/weixin_36474809/article/details/84566873
[FPGA_HLS_ 1]: https://blog.csdn.net/weixin_36474809/article/details/84580456
[FPGA_HLS]: https://blog.csdn.net/weixin_36474809/article/details/84940846
[FPGA_IPcore_HLS_bug_]: https://blog.csdn.net/weixin_36474809/article/details/84832760
[FPGA_IPcore_HLS_RTL_]: https://blog.csdn.net/weixin_36474809/article/details/84977743
[FPGA_vivado_ 1]: https://blog.csdn.net/weixin_36474809/article/details/84987176
[FPGA_IPcore_BRAM_ReLU]: https://blog.csdn.net/weixin_36474809/article/details/85257372
[FPGA_WBRAM_]: https://blog.csdn.net/weixin_36474809/article/details/86130778
[IPcore_]: https://blog.csdn.net/weixin_36474809/article/details/85271940
[Hi3516_]: https://blog.csdn.net/weixin_36474809/article/details/80832631
[FPGA_PS_SDK_DMA]: https://blog.csdn.net/weixin_36474809/article/details/81028275
[Xilinx zynq_FPGA_]: https://blog.csdn.net/weixin_36474809/article/details/80894801
[zynq_]: https://blog.csdn.net/weixin_36474809/article/details/86517747
[FLOPS_GOPS_]: https://blog.csdn.net/weixin_36474809/article/details/85675504
[DNNDK_]: https://blog.csdn.net/weixin_36474809/article/details/82585091