简介:轻量级神经网络开源库。适用于部署到有限计算资源设备的深度学习算法。
安装:
- 克隆源码库
git clone https://github.com/tiny-dnn/tiny-dnn
-
使用编译工具cmake生成makefile文件
安装cmake工具:
教程(Ubuntu 18.04下安装最新CMake及CMake简单使用) -
若要执行tiny-dnn里面的项目或测试单元,执行以下命令
cd tiny-dnn
cmake -BUILD_EXAMPLES=ON -BUILD_TESTS=ON .
make
结果:examples文件夹中出现可执行文件。
- 运行可执行文件
(需要有data和4.bmp文件)
# 训练mnist数据集
./examples/example_mnist_train data
# 训练图片识别
./examples/example_mnist_test examples/4.bmp
- 使用示例
构造卷积神经网络:
#include "tiny_dnn/tiny_dnn.h" // 相对位置(对于下载的./tiny_dnn/tiny_dnn/tiny_dnn.h)
using namespace tiny_dnn;
using namespace tiny_dnn::activation;
using namespace tiny_dnn::layers;
void construct_cnn() {
using namespace tiny_dnn;
network<sequential> net;
// add layers
net << conv(32, 32, 5, 1, 6) << tanh() // in:32x32x1, 5x5conv, 6fmaps
<< ave_pool(28, 28, 6, 2) << tanh() // in:28x28x6, 2x2pooling
<< fc(14 * 14 * 6, 120) << tanh() // in:14x14x6, out:120
<< fc(120, 10); // in:120, out:10
assert(net.in_data_size() == 32 * 32);
assert(net.out_data_size() == 10);
// load MNIST dataset
std::vector<label_t> train_labels;
std::vector<vec_t> train_images;
parse_mnist_labels("train-labels.idx1-ubyte", &train_labels);
parse_mnist_images("train-images.idx3-ubyte", &train_images, -1.0, 1.0, 2, 2);
// declare optimization algorithm
adagrad optimizer;
// train (50-epoch, 30-minibatch)
net.train<mse, adagrad>(optimizer, train_images, train_labels, 30, 50);
// save
net.save("net");
// load
// network<sequential> net2;
// net2.load("net");
}
创建多层感知器(mlp)
#include "tiny_dnn/tiny_dnn.h"
using namespace tiny_dnn;
using namespace tiny_dnn::activation;
using namespace tiny_dnn::layers;
void construct_mlp() {
network<sequential> net;
net << fc(32 * 32, 300) << sigmoid() << fc(300, 10);
assert(net.in_data_size() == 32 * 32);
assert(net.out_data_size() == 10);
}
创建mlp的另一种方式:
#include "tiny_dnn/tiny_dnn.h"
using namespace tiny_dnn;
using namespace tiny_dnn::activation;
void construct_mlp() {
auto mynet = make_mlp<tanh>({ 32 * 32, 300, 10 });
assert(mynet.in_data_size() == 32 * 32);
assert(mynet.out_data_size() == 10);
}
注:若遇到与头文件路径相关的报错,可以用下面修改过的文件安装(放在/home下)
链接: https://pan.baidu.com/s/1zFNB5uBi5-K7HZALxuCcqg?pwd=bnkq 提取码: bnkq 复制这段内容后打开百度网盘手机App,操作更方便哦