登录
首页 » matlab » yechengxi-LightNet-6ada9dd

yechengxi-LightNet-6ada9dd

于 2020-01-20 发布
0 193
下载积分: 1 下载次数: 11

代码说明:

说明:  一个matlab神经网络工具箱,其中包含RNN,CNN等(Matlab neural network toolbox)

文件列表:

yechengxi-LightNet-6ada9dd, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CNN, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CNN\Main_CIFAR_CNN_SGD.m, 674 , 2017-10-21
yechengxi-LightNet-6ada9dd\CNN\Main_CNN_ImageNet_minimal.m, 1194 , 2017-10-21
yechengxi-LightNet-6ada9dd\CNN\PrepareData_CIFAR_CNN.m, 413 , 2017-10-21
yechengxi-LightNet-6ada9dd\CNN\getCifarImdb.m, 2122 , 2017-10-21
yechengxi-LightNet-6ada9dd\CNN\net_init_cifar_cnn.m, 1849 , 2017-10-21
yechengxi-LightNet-6ada9dd\CNN\test_im.JPG, 113805 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\activations, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\activations\leaky_relu.m, 245 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\activations\modu.m, 310 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\activations\relu.m, 143 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\activations\sigmoid_ln.m, 149 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\activations\tanh_ln.m, 152 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\bnorm.m, 3375 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\conv_layer_1d.m, 5449 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\conv_layer_2d.m, 5367 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\dropout.m, 277 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\linear_layer.m, 2436 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\lrn.m, 2430 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\maxpool.m, 3523 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\maxpool_1d.m, 2936 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\rmsnorm.m, 2099 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\layers\softmax.m, 254 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\loss, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\loss\softmaxlogloss.m, 551 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\net, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\net\Main_Template.m, 3119 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\net\TrainingScript.m, 3614 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\net\net_bp.m, 5983 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\net\net_ff.m, 6106 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\net\test_net.m, 3978 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\net\train_net.m, 4654 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim\adagrad.m, 2055 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim\adam.m, 3192 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim\gradient_decorrelation.m, 3624 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim\rmsprop.m, 2991 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim\select_learning_rate.m, 2321 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim\selective_sgd.m, 867 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim\sgd.m, 2378 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\optim\sgd2.m, 5401 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\SwitchProcessor.m, 565 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\average_gradients_in_frames.m, 942 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\error_multiclass.m, 689 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\flipall.m, 80 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\generate_output_filename.m, 947 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\im2col_ln.m, 1267 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\pad_data.m, 866 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\pad_data_1d.m, 686 , 2017-10-21
yechengxi-LightNet-6ada9dd\CoreModules\util\unroll_ln.m, 858 , 2017-10-21
yechengxi-LightNet-6ada9dd\Documentations, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\Documentations\LightNet Tutorial.pptx, 1285467 , 2017-10-21
yechengxi-LightNet-6ada9dd\Documentations\lightnet-supplementary-materials.pdf, 172375 , 2017-10-21
yechengxi-LightNet-6ada9dd\Documentations\lightnet-versatile-standalone.pdf, 373087 , 2017-10-21
yechengxi-LightNet-6ada9dd\ImageNetPreTrain.png, 312780 , 2017-10-21
yechengxi-LightNet-6ada9dd\Init.png, 51249 , 2017-10-21
yechengxi-LightNet-6ada9dd\License.txt, 736 , 2017-10-21
yechengxi-LightNet-6ada9dd\LightNet.png, 84805 , 2017-10-21
yechengxi-LightNet-6ada9dd\Log.txt, 2348 , 2017-10-21
yechengxi-LightNet-6ada9dd\MLP, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\MLP\Main_MNIST_MLP_Dropout.m, 923 , 2017-10-21
yechengxi-LightNet-6ada9dd\MLP\Main_MNIST_MLP_RMSPROP.m, 918 , 2017-10-21
yechengxi-LightNet-6ada9dd\MLP\PrepareData_MNIST_MLP.m, 665 , 2017-10-21
yechengxi-LightNet-6ada9dd\MLP\get_mnist.m, 1620 , 2017-10-21
yechengxi-LightNet-6ada9dd\MLP\net_init_mlp_mnist.m, 967 , 2017-10-21
yechengxi-LightNet-6ada9dd\MLP\net_init_mlp_mnist_dropout.m, 1668 , 2017-10-21
yechengxi-LightNet-6ada9dd\README.md, 5613 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\Main_Char_RNN.m, 4440 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\gru_bp.m, 1780 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\gru_ff.m, 2349 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lm_data, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lm_data\PrepareData_Char_RNN.m, 561 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lm_data\dict.txt, 147 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lm_data\test_x.txt, 1118891 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lm_data\test_y.txt, 1118891 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lm_data\train_x.txt, 1997710 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lm_data\train_y.txt, 1997710 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lstm_bp.m, 1947 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\lstm_ff.m, 2582 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\net_init_char_gru.m, 1228 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\net_init_char_lstm.m, 1351 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\net_init_char_qrnn.m, 1197 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\net_init_char_rnn.m, 877 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\qrnn_bp.m, 1350 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\qrnn_ff.m, 1883 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\rnn_bp.m, 1138 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\rnn_ff.m, 2129 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\test_rnn.m, 1209 , 2017-10-21
yechengxi-LightNet-6ada9dd\RNN\train_rnn.m, 4898 , 2017-10-21
yechengxi-LightNet-6ada9dd\ReinforcementLearning, 0 , 2017-10-21
yechengxi-LightNet-6ada9dd\ReinforcementLearning\Cart_Pole.m, 1138 , 2017-10-21
yechengxi-LightNet-6ada9dd\ReinforcementLearning\Main_Cart_Pole_Policy_Network.m, 4506 , 2017-10-21
yechengxi-LightNet-6ada9dd\ReinforcementLearning\Main_Cart_Pole_Q_Network.m, 4754 , 2017-10-21
yechengxi-LightNet-6ada9dd\ReinforcementLearning\is_valid_state.m, 273 , 2017-10-21
yechengxi-LightNet-6ada9dd\ReinforcementLearning\net_init_pole.m, 509 , 2017-10-21

下载说明:请别用迅雷下载,失败请重下,重下不扣分!

发表评论

0 个回复

  • 2660
    这是关于MATlab的一个PDF文档,这个文档清晰的给出了 Matlab的使用方法 (This is on the Matlab a PDF document, the document gives a clear use of Matlab)
    2008-07-31 11:24:51下载
    积分:1
  • daubcomp
    应用小波进行压缩和滤波的matlab程序.程序选用Daubechies的仅4个系数的小波函数,也可选用其他小波函数,详见说明。(wavelet compression and filtering of Matlab procedures. Procedures for the selection of Daubechies only four coefficients of wavelet function can also choose other wavelet function, as described in note.)
    2006-12-26 17:07:01下载
    积分:1
  • bian-cheng
    m、W序列的产生及仿真,扩频复合系统的源程序(m and W sequence generation and simulation, source of spread spectrum composite systems)
    2012-05-09 10:21:53下载
    积分:1
  • New-folder-(5)
    this file is about beam forming with adaptive file
    2013-09-12 15:49:54下载
    积分:1
  • cepst
    cepstral analisys for pitch and F0 detection
    2009-02-17 02:50:40下载
    积分:1
  • Resultats
    Compression Denoising enhanced procedures for your reference. Include: digital image data display matrix and its Fourier transform two-dimensional discrete cosine transform image compression method using gray-scale transformation of the contrast-enhanced images using two-dimensional median filter function by medfilt2 of salt and pepper noise image filtering using MATLAB The function affected by noise interference filter2 images mean filter Adaptive Image Filtering Wehner use five kinds of different gradient method to enhance image sharpening images of high-pass filtering and mask treatment using Butterworth (Butterworth) low pass filter noise by smoothing the images deal with the use of Butterworth (Butterworth) high-pass filter for sharpening images treatment
    2010-10-19 05:51:39下载
    积分:1
  • SourceEncoingAndDecoding
    说明:  通过信源编译码,理解信源编码的主要目的,理解香农第一定理,掌握信源编码的方法和手段(By source encoding and decoding, source code to understand the main purpose of the first theorem of Shannon to understand and master the methods and source code means)
    2010-04-14 17:30:47下载
    积分:1
  • section_to_plane
    这个主要是我所做的一段matlab代码,主要实现剖面上的数据在平面上求解的过程(this I was doing a Matlab code, main profile in the data plane for the course)
    2006-12-13 17:47:21下载
    积分:1
  • EEMD
    关于经验模态分解的一个程序,主要实现EEMD分解过程(On empirical mode decomposition of a program, the main decomposition process to achieve EEMD)
    2011-11-11 18:02:57下载
    积分:1
  • DWT
    对音频信号进行DWT变换,可嵌入水印信息(DWT transform audio signals can be embedded watermark)
    2010-09-02 14:09:03下载
    积分:1
  • 696516资源总数
  • 106554会员总数
  • 12今日下载