搜索资源列表
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
CNNWB_05-27-2012
- 这个是我找到的卷积神经网络在minist库上数字识别最好的结果，准确率99.5 ，比C++版本的更好。程序可以直接编译运行，但是因为要下载两个数据库可能非常慢，需要你修改一下代码跳过去。如果你对cnn很感兴趣，可以找我Q:3617 28654-This is what I found convolutional neural network minist library Digital Identification best results, the accuracy was 99.5 , be
DeepLearnToolbox-master
- deep learning 包含CAE CNN NN SAE和DBN算法-deep learning includes CAE CNN NN SAE and DBN algorithms
CNN.tar
- 卷积神经网路 包括了MLP层，conv层，pooling层，RBM层，LRN层，采用xml配置文件设置参数，实现训练识别-Convolution neural network, including the MLP layer, conv layer, pooling layer, RBM layer, LRN layer, using xml configuration file to set parameters to achieve recognition training
caffe-master
- 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-one open source code of CNN which can extract features other image dataset.
CNN
- 用MATLAB实现卷积神经网络，并对图像进行特征提取-Using MATLAB convolution neural networks, and image feature extraction
CUDA-CNN-master
- CNN cuda的加速。 start-of-art结果的流行的数据集 1。测试mnist并获得99.76 ,投票后(99.82 )(最好的99.79 ) 2。测试cifar-10并获得81.42 最好(90 ) 3。测试cifar - 100和51.13 (最好的65 )-CNN accelerated by cuda. The start-of-art result s of popular datasets 1. Test on mnist and get 99.76
source-code
- 用D-CNN的方法，即CNN卷积层加Fisher Vector做图像分类的MATLAB代码-Use D-CNN approach ( Fisher Vector follows results of CNN convolutional layer as the image feature) to classificate the image
mycnn
- 卷积神经网络识别字符的Matlab程序，包含所需的所有素材和自己改进的一部分代码-Convolutional neural network for handwriten digits recognition: training and simulation. This program implements the convolutional neural network for MNIST handwriten digits recognition, created by Yan
CNN-
- CNN卷积神经网络数字识别MATLAB代码-CNN convolutional neural network digital identification MATLAB code
CNN-facelable
- 用CNN实现人脸标注,是适用于人脸识别及人脸检测-using CNN for Facelable，for face recognition or face detection.
CNN
- 卷积神经网络代码，Java版。改自Deep Learning Toolbox的matlab代码。-CNN code with Java. From github deep learning toolbox
CNN(cPP)
- theano的C++实现，先用theano训练完，然后调用训练后的参数即可-python c++ cnn
CNN for Image Retrieval Using MatConvNet.tar
- 使用深度学习框架-MatConvNet实现图像检索(Code for image retrieval using MatConvNet (a popularDeep Learning framework))
Deep-Learning-ToolBox-CNN-master
- 实现CNN的手写字体matlab程序，可调节激活函数，选择loss函数(Realization of handwritten font matlab CNN procedures, can regulate the activation function, loss function)
程序源码
- 基于CNN的手势识别，可识别五种手势，拳头，手掌，比V，OK，还有空。要求环境：opencv，keras，theano，python2.7(CNN based gesture recognition can identify five kinds of gestures, fist, palms, than V, OK, and empty. Requirements for the environment: opencv, keras, theano, python2.7)
cnn
- 基于python tensorflow框架构建的卷积神经网络用来识别图像，附带训练数据集的制作代码。(The convolution neural network based on the python tensorflow framework is used to identify images with the production code of the training data set.)
MNIST
- 用CNN识别MNIST数据集，test集正确率98.3%(Identifying MNIST datasets with CNN)
cnn人脸识别
- 用卷积神经网络做的人脸识别，准确率达到92.75%。(The accuracy of face recognition using convolution neural network is 92.75%.)
cnn-edge-detection
- 卷积神经网络实现图像的边缘检测+python代码(CNN-edge-detection-python-codes)