搜索资源列表
kmeans_demo
- 关于CIFAR的K-means特征学习算法-K-means feature learning on CIFAR
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
cifar10inspect
- 采用卷积神经网络在cifar-10图像库上进行的分类训练。效果非常好。-Convolution using trained neural network classification on cifar-10' s image library. The effect is very good.
CNNWB
- 用C#语言实现的网上卷积神经元网络。包含全部源码，供大家学习之用。另外，本事例还带有CIFAR-10数据，只要装有VS 2013就可以使用。-On- line Convolution Neural Network Based on. Contains all the source code for everyone to learn. In addition, this case also comes with CIFAR-10 data, as long as equipped with VS
cascadeCNN_license_plate_detection-master
- 很好的一个车牌检测程序,检测率很高，快速卷积神经网络SoftwareMatlab R2016b Matlab R2016b(plate lisence detectionMatlab lesson design for vehicle detection and recognition. Using cifar-10Net to training a RCNN, and finetune AlexNet to classify. Thanks to Cars Dataset : http:/
CNTK
- 在深度的重要性的驱使下，出现了一个新的问题：训练一个更好的网络是否和堆叠更多的层一样简单呢？解决这一问题的障碍便是困扰人们很久的梯度消失/梯度爆炸，这从一开始便阻碍了模型的收敛。归一初始化（normalized initialization）和中间归一化（intermediate normalization）在很大程度上解决了这一问题，它使得数十层的网络在反向传播的随机梯度下降（SGD）上能够收敛。 当深层网络能够收敛时，一个退化问题又出现了：随着网络深度的增加，准确率达到饱和（不足为奇）然后迅
CNN_tf_demo
- 这是一段卷积神经网络水水水水水水水水水水水水水(We summarize hyperparameters used for the ImageNet model in Table 1 and for the CIFAR-10 model in Table 2)
resnet
- 使用 TensorFlow 实现 resNet, 也就是残差网络，为官方demo， 分别用 cifar 数据集和 ImageNet 数据集进行测试。(Using TensorFlow to achieve resNet, that is, the residual network, for official demo, respectively, using cifar data sets and ImageNet data sets for testing.)
ResNet_cifar-master
- resnet 在tensorflow上的实现，基于cifar10，cifar100数据集(Implementation of RESNET on tensorflow, based on cifar10, cifar100 data sets)
nn_CIFAR.py
- pytorch tutorial 代码 简单神经网络 数据集CIFAR(pytorch nn training sample code, Dataset: CIFAR dataset Usage: python3 nn_CIFAR.py)
image
- cifar 卷积神经网络 通过cnn识别图片，对神经网络进行训练，在识别cifar库(convolutional neural network)
code
- 不同的网络结构解决cifar-100图像识别(Different network structures to solve cifar-100 image recognition)
test_CNN
- 卷积神经网络，简单的对cifar数据集进行分类的代码(convolutional neural network)
tensorflow-CNN-CIFAR-10-master
- CNN实现图像数据的分类，有数据库下载代码(CNN implements the classification of image data, and there is a database download code)
mxnetcnn-master
- 利用mxnet构建cnn，对cifar-10 图片进行分类识别(Using mxnet to construct CNN for classification and recognition of cifar-10 pictures)
cnn
- TensorFlow框架下cnn 对数据集cifar分类问题(CNN classification for data sets cifar)
CIFAR10
- 在CIFAR-10数据集上使用卷积神经网络进行图像分类(Image classification using convolution neural network on CIFAR-10 dataset)
04.CNN处理CiFar
- 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.)
cifar-10-cnn-master
- 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)
cifar-vgg-master图像识别
- cifar-vgg-master图像识别，基于python平台，很好用(cifar-vgg-master image recognition)