搜索资源列表
BP-predict
- 针对中长期电力负荷预测样本量小、多因素影响的特点,利用灰色关联度筛选影响因素,建立基于BP 神经网络算法的负荷预测模型,通过多因素变量及历史负荷变量序列进行滚动预测,得到的预测值明显优于 单一预测方法,并通过马尔可夫过程对预测残差进行修正,使预测精度得到较大提高,研究实证表明,这种预 测方法具有进行推广应用的价值 -For long-term load forecasting small sample size, the
BP2BE
- 基于BP神经网络的盲均衡器设计， 采用BP神经网络进行盲均衡 残差小，误码率低-blind equalizationo based n bp neural networks
BPcanchayuce
- 基于ＢＰ神经网络的残差值预测，根据已经得到的残差实际值结合ＢＰ神经网络模型进行仿真，得出预测数据-Based on the residual value of the BP neural network prediction, according to the residual has actual value simulation combined with BP neural network model, forecast data
deep-residual-networks-master
- 深度残差网络的介绍与源代码，适合深度学习爱好者学习。这是何凯明大牛的又一部大作。-The depth of the residual network is introduced with the source code , suitable for deep learning lovers to study . This is another masterpiece He Kaiming Daniel .
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)
rcnn-master
- 残差网络模型,通过将原始输入直接通过桥梁输送到后面的几层，减少梯度弥散(The residual network model reduces the gradient dispersion by transmitting the original input directly through the bridge to the latter layers)
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
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
deep-residual-networks-master
- 深度残差网络实现代码，有何凯明在2015年提出的残差网络，映入了自我影射，解决了深度网络的退化问题(deep residual network)
fb.resnet.torch-master
- facebook公司开发的基于torch的残差网络深度学习模型(Torch based depth learning model based on residual network developed by Facebook company)
ResNeXt-Tensorflow-master
- 是残差网络的延伸，已经存在的网络。内容是可以运行的。(An extension of a residual network is an existing program.)
Residual-Networks
- 残差神经网络的Python实现,用于机器学习的图像识别方向。(Python implement on Residual Network)
利用残差网络进行图像融合
- 利用深度学习的方法进行红外图像和可见光图像的融合，该方法受启发于最近比较流行的迁移学习，利用可见光的数据集训练网络，从而提取出红外和可见光图像的特征，最后进行图像的融合。
tensorflow-resnet-master
- 残差神经网络的代码，可以用，非常好，，，，，，。(resual CNN about deep learning ,very good.........................)
Residual_Neural_Network-master
- 实现了残差神经网的训练，在jubernotebook上运行(The training of residual neural network is realized and it runs on jubernotebook)
TF-resnet-master
- 使用残差网络进行迁徙学习，增加效率和精度(Using Residual Networks for Migration Learning to Increase Efficiency and Accuracy)
models
- 包含unet/google-v2/CNN等多种神经网络的模型(Multiple Neural Network Models)
深度学习实现零件缺陷检测源代码(1)
- 结合VGG和残差网络实现工业零件的缺陷检测，基于keras和tensorflow可以直接运行使用(The defect detection of industrial parts is realized by combining VGg and residual network. Based on keras and tensorflow, it can be used directly)