Hot Search : Source embeded web remote control p2p game More...
Location : Home Search - cnn
Search - cnn - List
DL : 0
使用CNN检测目标 基于Tensorflow目标检测API(Uses CNN to detect objects. Based on Tensorflow Object Detection API)
Update : 2024-05-17 Size : 2048 Publisher : soarby

DL : 0
包含unet/google-v2/CNN等多种神经网络的模型(Multiple Neural Network Models)
Update : 2024-05-17 Size : 3072 Publisher : 嘟嘟佳

以python语言为基础,利用tensorflow机器学习架构,两层卷积神经网络实现,CiFar数据集图片分类功能。(Based on Python language, using tensorflow machine learning architecture, two-layer convolutional neural network, CiFar data set image classification function.)
Update : 2019-06-04 Size : 2048 Publisher : 奋斗到天亮

经典数据集分类,利用卷积神经网络分类,利用python语言编写(classic picture classification)
Update : 2024-05-17 Size : 1796096 Publisher : 那里有只猫

深度学习进行调制识别的数据集,用于卷积神经网络(dataset for cnn include generate_RML2016.04c and generate_RML2016.10a)
Update : 2024-05-17 Size : 7168 Publisher : monster123

CNN,DBN算法可以对手写体数字进行识别,准确率高(CNN and DBN algorithm can recognize handwritten numerals with high accuracy)
Update : 2024-05-17 Size : 29563904 Publisher : 迟画

DL : 0
基于卷积神经网络的无限电调制方式识别,数据集由软件无线电产生(Recognition of infinite electrical modulation based on convolutional neural network. Data sets are generated by software radio)
Update : 2024-05-17 Size : 36864 Publisher : wzlin123

DL : 0
使用卷积神经网络进行高光谱遥感数据分类,使用的数据源为Pavia University高光谱数据 文件夹log--日志文件夹,存放TensorBorad日志、网络参数文件、混淆矩阵图 文件夹Patch--存放数据处理的切片结果 文件夹PaviaU--高光谱数据下载存放位置 文件夹predicted--CNN对原始影像的分类结果 data.py--对原始高光谱影像进行数据处理,生成切片 net.py--神经网络模型 train.py--训练神经网络 utils.py--需要用到的函数 show.py--使用训练好的神经网络模型对原始数据进行分类(Using convolution neural network to classify hyperspectral remote sensing data, the data source is Pavia University hyperspectral data. Folder log -- Log folder, store TensorBorad logs, network parameter files, obfuscation matrix diagrams Folder Patch -- Stores slice results of data processing Folder PaviaU -- Place for Hyperspectral Data Download and Storage Folder predicted -- CNN classification results of original images Data.py -- Data processing of original hyperspectral images to generate slices Net.py--Neural Network Model Train.py--Training Neural Network Utils. py -- Functions to be used Show.py -- Classification of raw data using trained neural network model)
Update : 2024-05-17 Size : 9216 Publisher : 555644

OtherDeep
DL : 1
本文提出了一种用于通信系统中无线电信号检测的自动调制识别框架。该框架考虑了深度卷积神经网络(CNN)和长期短期记忆网络(LSTM)。 此外,我们提出了一种预处理信号表示,其组合了调制信号的同相,正交和四阶统计。所提供的数据表示允许我们的CNN和LSTM模型对我们的测试数据集实现8%的改进。(Automatic Modulation Recognition using Deep Learning Architectures, 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC))
Update : 2024-05-17 Size : 17408 Publisher : 撸代码

Fast R-CNN是在R-CNN的基础上进行的改进,大致框架是一致的。总体而言,Fast R-CNN相对于R-CNN而言,主要提出了三个改进策略: 1. 提出了RoIPooling,避免了对提取的region proposals进行缩放到224x224,然后经过pre-trained CNN进行检测的步骤,加速了整个网络的learning与inference过程,这个是巨大的改进,并且RoIPooling是可导的,因此使得整个网络可以实现end-to-end learning,这个可以认为是Fast R-CNN相对于R-CNN最大的改进之处。 2. 采用了Multi-task loss进行边框回归,这个在R-CNN中也有这方面的实验。 3. 利用了截断的奇异值分解(Truncated SVD for faster detection)加速了网络。(Fast r-cnn is an improvement based on r-cnn, and the general framework is consistent. In general, fast r-cnn, compared with r-cnn, mainly proposes three improvement strategies: 1. Proposed roipooling to avoid scaling the extracted region proposals to 224x224, and then accelerated the learning and information process of the whole network through pre trained CNN detection steps. This is a huge improvement, and roipooling is derivable, so that the whole network can achieve end-to-end learning, which can be considered as fast r-cnn relative to r-cnn- CNN's biggest improvement. 2. Multi task loss is used for border regression, which is also tested in r-cnn. 3. The truncated SVD for fast detection is used to accelerate the network.)
Update : 2024-05-17 Size : 290816 Publisher : xingfu1223

卷积神经网络实现CWRU滚动轴承数据集故障分类(Fault classification of volume and network)
Update : 2024-05-17 Size : 1024 Publisher : CuiML

卷积神经网络,可以很好的实现文本分类或者图像识别(Convolutional Neural Networks)
Update : 2024-05-17 Size : 11516928 Publisher : nimoxiaqian

本例程是我研究生阶段做的一个小项目,该项目用pytorch的深度学习框架来进行人体姿态识别,能够实现头部和身体的骨架识别!图像处理方面加入了OpenCV包进行相关的处理,希望能帮助大家!(175/5000 This routine is a small project that I did in the graduate stage. The project uses pytorch's deep learning framework to recognize human body posture, and can realize skeleton recognition of head and body! In the aspect of image processing, OpenCV package has been added for relevant processing, hoping to help everyone!)
Update : 2024-05-17 Size : 3126272 Publisher : linmi

手写体识别 lenet5 LeNet5由7层CNN(不包含输入层)组成,上图中输入的原始图像大小是32×32像素,卷积层用Ci表示,子采样层(pooling,池化)用Si表示,全连接层用Fi表示。下面逐层介绍其作用和示意图上方的数字含义。(Lenet5 is composed of seven layers of CNN)
Update : 2024-05-17 Size : 513024 Publisher : 659+59

为了自动学习CNN的深度网络结构,网络结构的数量随着网络中间层数量的增加呈指数增长,这启发我们使用遗传算法有效地遍历这个大的搜索空间。我们首先提出一种编码方法,将每个网络结构表示为一个固定长度的二进制字符串,然后通过生成一组随机个体来初始化遗传算法。在每一代中,我们定义标准的遗传操作(如选择、突变和交叉)来消除弱势个体并产生更具竞争力的个体。(In order to automatically learn the deep network structure of CNN, the number of network structure increases exponentially with the increase of the number of network middle layer, which inspires us to use genetic algorithm to effectively traverse this large search space.We first propose a coding method to represent each network structure as a binary string of fixed length, and then initialize the genetic algorithm by generating a set of random individuals.In each generation, we define standard genetic operations (such as selection, mutation, and crossover) to eliminate vulnerable individuals and produce more competitive ones.)
Update : 2024-05-17 Size : 8192 Publisher : 崔宁敏

基于卷机神经网络的文本信息提取应用的设计与实现,cn(Design and Implementation of Text Information Extraction Application Based on Reel Neural Network)
Update : 2024-05-17 Size : 12288 Publisher : 阿飞aaaaaa

使用神经网络进行训练,对高光谱普图像进行分类(Using neural network to train and classify hyperspectral images)
Update : 2024-05-17 Size : 27648 Publisher : Lyot

可以将训练权重.h文件转化为.weights文件,方便不同平台使用(The training weight. H file can be converted into. Weights file, which is convenient for different platforms)
Update : 2024-05-17 Size : 7168 Publisher : 王爽哈哈哈哈

DL : 0
卷积神经网络进行故障诊断,机械设备智能故障诊断(CNN for fault diagnosis)
Update : 2024-05-17 Size : 1024 Publisher : leon_guo

使用一维卷积神经网络处理序列数据,数据类型为一维(One dimensional convolution processing sequence data)
Update : 2024-05-17 Size : 33212416 Publisher : xmu南南
« 1 2 ... 23 24 25 26 27 2829 »
DSSZ is the largest source code store in internet!
Contact us :
1999-2046 DSSZ All Rights Reserved.