搜索资源列表
resnet
- 深度残差网络ResNet,分别有50,101,152,200层(The depth residual network ResNet, respectively, has 50101152200 layers)
resnet-protofiles-master
- 卷积神经网络resnet18、resnet34、resnet50、resnet101、resnet152的配置文件(网络结构和解决方案文件)(Convolution neural network resnet18, resnet34, resnet50, resnet101, resnet152 configuration file (network structure and solution file))
vgg16
- 在使用深度神经网络时我们一般推荐使用大牛的组推出的和成功的网络。如最近的google团队推出的BN-inception网络和inception-v3以及微软最新的深度残差网络ResNET。(In the use of deep neural network we generally recommend the use of cattle group launched and successful network. Such as the recent google team launched B
cat_vs_dog
- 利用神经网络模型Resnet模型对猫和狗进行识别(Recognition of cats and dogs by using neural network Resnet model.)
DenseNet-master
- 这篇文章是CVPR2017的oral,非常厉害。文章提出的DenseNet(Dense Convolutional Network)主要还是和ResNet及Inception网络做对比,思想上有借鉴,但却是全新的结构,网络结构并不复杂,却非常有效!众所周知,最近一两年卷积神经网络提高效果的方向,要么深(比如ResNet,解决了网络深时候的梯度消失问题)要么宽(比如GoogleNet的Inception),而作者则是从feature入手,通过对feature的极致利用达到更好的效果和更少的参数。(
tensorflow-resnet-master
- ResNet在2015年被提出,在ImageNet比赛classification任务上获得第一名,因为它“简单与实用”并存,之后很多方法都建立在ResNet50或者ResNet101的基础上完成的,检测,分割,识别等领域都纷纷使用ResNet,Alpha zero也使用了ResNet,所以可见ResNet确实很好用。(ResNet was proposed in 2015 and won the first place in the classification task of ImageNe
symbol_resnet
- RACNN注意力机制,细腻度图片分类。 RA-CNN由上到下用了3个尺度并且越来越精细,尺度间构成循环,即上层的输出作为当层的输入。RA-CNN主要包含两部分:每一个尺度上的卷积网络和相邻尺度间的注意力提取网络(APN, Attention Proposal Network)。在每一个尺度中,使用了堆叠的卷积层等,最后接上全连接层于softmax层,输出每一个类别的概率;这个是很好理解的,代码采用的网络结构是VGG的网络结构。(RACNN attention mechanism)
ASVspoof2019_keras
- 一个基于kera的resnet神经网络的baseline(A baseline of RESNET neural network based on Kera)
ResNet-Tensorflow-master
- 使用tensorflow框架对高光谱图像进行识别、分类(Recognition and classification of hyperspectral images using densenet structure)
深度学习mtcnn
- 用市面上的摄像头,可以实现实时人脸识别功能。(The algorithm model of facenet face recognition is obtained through deep learning, and the backbone network of feature extraction is concept-resnetv1, which is developed from concept network and RESNET, with more channels and n
