搜索资源列表
GrowthtypeConvolutionNeuralNetworkandItsApplicatio
- 增长式卷积神经网络及其在人脸检测中的应用-Growth-type Convolution Neural Network and Its Application in Face Detection growth-type convolution neural network and its application in face detection growing type convolution neural network and its application in face detecti
LeNet
- 用于书写体数字识别的卷积神经网络，VC++源码，仅供学习参考-Convolutional Neural Networks in Handwritten Digit Recognition Visual C++ implemented.
ver_0.82
- 此文件包包含用卷积神经网络识别手写输入的识别程序，数据可从MNIST下载-This release includes sample of handwritten digits recognition using CNN. If you just want to try it run cnet_tool. You ll see a simple GUI. It loads pretrained convolutional neural net from cnet.mat and recognize
Pattern-Classification
- 此文档包含对卷积神经网络的描述及在图像处理中的应用，对学习卷积神经网络有重要帮助。-The work presented here uses image classifi cation performance (accurate discrimination between common classes of objects) as a basis for comparing visual system models, and algorithms for fi
mycnn
- 卷积神经网络算法 里面有一个例子 能扩展到大数据集上-Convolutional neural network algorithm
SceneTextCNN_demo.tar
- 端至端卷积神经网络的文字识别,代码演示包. 它包含我们的论文中使用的所有主要组成部分: kmeans无监督特征学习 + 卷积神经网络(CNN)-This is a demo package of the code we used for our paper, "End-to-End Text Recognition with Convolutional Neural Networks", T. Wang, D. Wu, A. Coates, A. Ng, in ICPR 2012.
DeepLearnToolbox-master
- 可以进行深度学习，卷积神经网络的一种开源代码，可以对图像数据库自动提取特征(You can do deep learning)
ShuffleNet-master
- 一种专门为移动端设备而设计的高效卷积神经网络结构——ShuffleNet，这种新结构将点态组卷积（pointwise group convolution）和通道随机混合（channel shuffle）这两种经典方法进行结合与改进，大大提升了计算效率 。(ShuffleNet is an efficient convolutional neural network designed for mobile terminal devices. This new structure combines
Two-Layer-CNN-on-MNIST-master
- 卷积神经网络的matlab实现，同时可以作为图像处理使用，用于csi室内定位(Convolution neural network matlab implementation, can also be used as image processing for csi indoor positioning)
writingMaster
- 实验室项目。识别用户签名和汉字草书，效果较好。基于卷积神经网络实现。框架是tensorflow。原创代码初次公开。(Laboratory project. The recognition of user signature and Chinese scr ipt is good. Based on convolution neural network implementation. The framework is tensorflow. Original code for the first
CNN_matlab
- 卷积神经网络（CNN）是一种深度学习方法，它可以对图像进行识别和特征分类等优点。(The convolution neural network (CNN) is a deep learning method which can identify and characterize the image.)
MNLIST and CNN
- 实现了在Mnist上的分类，使用了卷积神经网络(use convoluntional neural network to implement classificaiton on Minist.)
read+convolute+pool
- 关于卷积神经网络，读文件的代码，卷积的代码（并行优化过的）、池化的代码。(About convolutional neural network, read the file's code, convolution code (parallel optimization), pool code.)
Convolutional-Neural-Network-master
- matlab，深度学习工具箱，经典的卷积神经网络，共有两层卷积层。输入为28*28*1的图片(Matlab, the deep learning toolbox, the classic convolution neural network, has two volumes of layers. A picture entered into 28*28*1)
depth-map-prediction-
- 基于AlexNet网络模型的单幅彩色图的深度估计，在NYU Depth 数据集，Make3D 数据集，KITTI 数据集经过测试效果很好，只是本次上传由于大小限制，压缩包不包括数据集，读者可自行下载数据集进行训练！(Based on the AlexNet network model, the depth estimation of a single color map, in the NYU Depth dataset, Make3D dataset, KITTI dataset ha
CNN_v2
- 癫痫脑电图（EEG）异常波精准识别深度学习CNN卷积神经网络(Accurate Recognition of Epilepsy EEG Abnormal Waves and Deep Learning CNN Convolutional Neural Network)
去噪网络
- 去噪DNCNN卷积神经网络，可以用于信道估计，python代码，含有说明
一维CNN处理序列数据
- 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)
Basic_CNNs_TensorFlow2-master
- 使用TensorFlow框架书写的各主流CNN网络模型，没有数据集，可自行更改，能跑通(The mainstream CNN network models written by tensorflow framework have no data set and can be changed by themselves and can run through)
基于卷积神经网络的道路目标检测算法
- 针对实际交通场景下道路目标检测时存在检测精度低、检测速度慢以及难以检测小目标的问题，faster R-CNN的快速、精确道路目标检测算法。该算法包括一个精确目标区域网络 和一个目标属性学习网络通过引入反卷积结构，设计网络的损失函数，提高小目标的检测性能，为加快算法的计算速度。