SimpleNN is a simple neural network framework written in C++.It can help to learn how neural networks work.
源码地址：https://github.com/Kindn/SimpleNN
.netjson file,while weights will be saved as a .weightsbinary file..netfile and load weights from an existing .weights.Load dataset (including data and labels) from a .csvfile.It is neccesary to preprocess the dataset（mnist etc.) into SimpleNN stype 2D matrix and save it into a .csvfile.All data in SimpleNN will be organized into columns and conbined into a 2D matrix..net；权重存为二进制文件，扩展名为.weights。.net文件中加载网络，从已有的.weights文件中加载权重。.csv文件中加载数据集。在此之前需要对原始数据集(如mnist等）进行预处理组织为一个二维矩阵。例如，大多数情况下一批batch size为 N N N 的 C C C 通道 H H Hx W W W 图像会按通道展开成列并组织为一个 ( H ∗ W ) (H*W) (H∗W)x ( C ∗ N ) (C*N) (C∗N)的矩阵。
The core of SimpleNN is completely written with C++11 STL.So to build SimpleNN it just need a C++ compiler surppoting C++11 stantard.
P.S.:Some examples in examplesfolder needs 3rd-party libraries like OpenCV3.So if you want to build them as well you may install the needed libraries first.
Any os with C++11 compiler.
本来自己想到用C++实现神经网络主要是想强化一下编码能力并入门深度学习，所以我会尽力亲自从头实现以上功能，欢迎各位大佬们批评指点！
1.Build
git clone cd SimpleNN mkdir build cd build cmake .. make
2.Run examples(Linux)
examples都在examples目录下，以例子recognition为例。本例是利用图像分割和LeNet进行数字识别。
若目标数字是黑底白字，则在终端输入（假设终端在SimpleNN根目录下打开）
examples/mnist/recognition <image_path>
效果：
若目标数字是黑底白字，则输入
examples/mnist/recognition <image_path> --reverse
在mnist目录下已有训练好的LeNet权重参数。若要运行examples/mnist/train，需要先在examples/mnist/dataset目录下运行generate_csv.py来生成数据集的csv文件（这个文件有400多M属于大文件试了好多种都push不上来QAQ）。
注：本例依赖OpenCV3，如果要运行须事先安装，不然不会编译本例。
3.Coding
Construct network
int input_img_rows1 = 28;
int input_img_cols1 = 28;
int input_img_channels1 = 1;
int conv_output_img_channels1 = 6;
int conv_filter_rows1 = 5;
int conv_filter_cols1 = 5;
int conv_row_pads1 = 0;
int conv_col_pads1 = 0;
int conv_row_strides1 = 1;
int conv_col_strides1 = 1;
std::shared_ptr<snn::Convolution> conv_layer1(new snn::Convolution(input_img_rows1, input_img_cols1,
input_img_channels1,
conv_output_img_channels1,
conv_filter_rows1, conv_filter_cols1,
conv_row_pads1, conv_col_pads1,
conv_row_strides1, conv_col_strides1,
0, 0.283,
0, 0.01));
int pool_input_img_rows1 = conv_layer1->output_img_rows;
int pool_input_img_cols1 = conv_layer1->output_img_cols;
int pool_filter_rows1 = 2;
int pool_filter_cols1 = 2;
int pool_pads1 = 0;
int pool_strides1 = 2;
std::shared_ptr<snn::MaxPooling> pool_layer1(new snn::MaxPooling(pool_input_img_rows1, pool_input_img_cols1,
pool_filter_rows1, pool_filter_cols1,
pool_pads1, pool_pads1,
pool_strides1, pool_strides1,
conv_output_img_channels1, false));
int input_img_rows2 = pool_layer1->output_img_rows;
int input_img_cols2 = pool_layer1->output_img_rows;
int input_img_channels2 = pool_layer1->image_channels;
int conv_output_img_channels2 = 16;
int conv_filter_rows2 = 5;
int conv_filter_cols2 = 5;
int conv_row_pads2 = 0;
int conv_col_pads2 = 0;
int conv_row_strides2 = 1;
int conv_col_strides2 = 1;
std::shared_ptr<snn::Convolution> conv_layer2(new snn::Convolution(input_img_rows2, input_img_cols2,
input_img_channels2,
conv_output_img_channels2,
conv_filter_rows2, conv_filter_cols2,
conv_row_pads2, conv_col_pads2,
conv_row_strides2, conv_col_strides2,
0, 0.115,
0, 0.01));
int pool_input_img_rows2 = conv_layer2->output_img_rows;
int pool_input_img_cols2 = conv_layer2->output_img_cols;
int pool_filter_rows2 = 2;
int pool_filter_cols2 = 2;
int pool_pads2 = 0;
int pool_strides2 = 2;
std::shared_ptr<snn::MaxPooling> pool_layer2(new snn::MaxPooling(pool_input_img_rows2, pool_input_img_cols2,
pool_filter_rows2, pool_filter_cols2,
pool_pads2, pool_pads2,
pool_strides2, pool_strides2,
conv_output_img_channels2, true));
int aff1_input_rows = pool_layer2->output_rows * conv_output_img_channels2; // because flatten-flag is true
int aff1_input_cols = 1;
int aff1_output_rows = 120;
int aff1_output_cols = 1;
std::shared_ptr<snn::Affine> aff1_layer(new snn::Affine(aff1_input_rows, aff1_input_cols,
aff1_output_rows, aff1_output_cols, 0, 2.0 / double(aff1_input_rows),
0, 0.01));
int aff2_input_rows = 120;
int aff2_input_cols = 1;
int aff2_output_rows = 84;
int aff2_output_cols = 1;
std::shared_ptr<snn::Affine> aff2_layer(new snn::Affine(aff2_input_rows, aff2_input_cols,
aff2_output_rows, aff2_output_cols, 0, 2.0 / 120.0, 0, 0.01));
int aff3_input_rows = 84;
int aff3_input_cols = 1;
int aff3_output_rows = 10;
int aff3_output_cols = 1;
std::shared_ptr<snn::Affine> aff3_layer(new snn::Affine(aff3_input_rows, aff3_input_cols,
aff3_output_rows, aff3_output_cols, 0, 2.0 / 84.0, 0, 0.01));
std::shared_ptr<snn::Relu> relu_layer1(new snn::Relu);
std::shared_ptr<snn::Relu> relu_layer2(new snn::Relu);
std::shared_ptr<snn::Relu> relu_layer3(new snn::Relu);
std::shared_ptr<snn::Relu> relu_layer4(new snn::Relu);
//std::shared_ptr<Softmax> softmax_layer(new Softmax);
snn::Sequential net;
net << conv_layer1 << relu_layer1 << pool_layer1
<< conv_layer2 << relu_layer2 << pool_layer2
<< aff1_layer << relu_layer3
<< aff2_layer << relu_layer4
<<aff3_layer;
也可以直接封装成一个类，参考models目录下各hpp文件：
#include <../include/SimpleNN.hpp>
namespace snn
{
// Simplified LeNet-5 model
class LeNet : public Sequential
{
public:
LeNet():Sequential()
{
/* ... */
*this << conv_layer1 << relu_layer1 << pool_layer1
<< conv_layer2 << relu_layer2 << pool_layer2
<< aff1_layer << relu_layer3
<< aff2_layer << relu_layer4
<<aff3_layer;
}
};
}
Train model
配置优化器和loss层：
std::shared_ptr<SoftmaxWithLoss> loss_layer(new SoftmaxWithLoss(true)); net.set_loss_layer(loss_layer); std::cout << "Loss layer ready!" << std::endl; std::vector<Matrix_d> init_params = net.get_params(); std::vector<Matrix_d> init_grads = net.get_grads(); std::shared_ptr<AdaGrad> opt(new AdaGrad(init_params, init_grads, 0.012)); net.set_optimizer(opt);
加载数据
Dataset train_set(true);
Dataset test_set(true);
if (train_set.load_data(train_data_file_path, train_label_file_path))
std::cout << "Train set loading finished!" << std::endl;
else
std::cout << "Failed to load train set data!" << std::endl;
if (test_set.load_data(test_data_file_path, test_label_file_path))
std::cout << "Test set loading finished!" << std::endl;
else
std::cout << "Failed to load test set data!" << std::endl;
训练并保存模型
net.fit(train_set, test_set, 256, 2);
if (!net.save_net("../../../examples/mnist/LeNet.net"))
{
std::cout << "Failed to save net!" << std::endl;
return 0;
}
if (!net.save_weights("../../../examples/mnist/LeNet.weights"))
{
std::cout << "Failed to save weights!" << std::endl;
return 0;
}
Load model
if (!net.load_net(net_path))
{
std::cerr << "Failed to load net!" << std::endl;
return -1;
}
if (!net.load_weights(weight_path))
{
std::cerr << "Failed to load weights!" << std::endl;
return -1;
}
或者直接
if (!net.load_model(net_path, weight_path))
{
std::cerr << "Failed to load model!" << std::endl;
return -1;
}
如果网络结构和权重分开加载，则先加载结构再加载权重。
Predict
y = net.predict(x);
