HG Beam

说明：  BP神经网络实现手写数字识别，以包含字库，字库内容有改动，方便测试识别结果(BP Neural Network realizes handwritten numeral recognition to include a font, the content of the font is changed, and it is convenient to test the recognition results.)

此程序是北斗精密单点定位的相关程序，其中包括坐标的转换，滤波以及各个误差模型的改正(This program is Beidou precise single-point positioning of the relevant procedures, including coordinate conversion, filtering and correction of the various error models)

这是我最近写的图书馆管理系统，很不错的，大家可以下来-This what I recently wrote a library management system that is very good, we can look at down

本程序实现了一个简单的数读程序的解决方法，还不错的。-This procedure implements a few simple procedures for the solution time, but also good.

二十份精选的简历模板，需要的可以下载看看(Twenty Selected Resume Templates)

好可以程序控制打开或关闭CDROM，非常方便(2KB)-Good can control open or close the CDROM, very convenient (2KB)

pfc2d单轴压缩实验二维代码 可以直接运行 包含多种粘结模型(Uniaxial compression experiment of PFC 2D)

computes the throughput in a cognitive radio network

cascaded 12 level converter(cascaded 12 level converter dv)

说明：  裂纹是典型的线结构，在许多计算机视觉应用中都很有趣。在实际应用中，路面裂缝等许多裂缝连续性差、对比度低，给利用低层特征进行基于图像的裂缝检测带来了很大的挑战。在本文中，我们提出了深度裂纹——一个端到端可训练的深度卷积神经网络，通过学习用于裂纹表示的高级特征来自动检测裂纹。该方法将在层次卷积阶段学习到的多尺度深度卷积特征融合在一起，以获取线路结构。更详细的表示在大比例尺的feature maps中进行，更全面的表示在小比例尺的feature maps中进行。我们在SegNet的编码器解码器架构上构建深度裂纹网，并对在相同尺度下在编码器网络和解码器网络中生成的卷积特征进行配对融合。(Cracks are typical line structures that are of interest in many computer-vision applications. In practice, many cracks, e.g., pavement cracks, show poor continuity and low contrast, which bring great challenges to image-based crack detection by using low-level features. In this paper, we propose DeepCrack---an end-to-end trainable deep convolutional neural network for automatic crack detection by learning high-level features for crack representation. In this method, multi-scale deep convolutional features learned at hierarchical convolutional stages are fused together to capture the line structures. More detailed representations are made in larger scale feature maps and more holistic representations are made in smaller scale feature maps. We build DeepCrack net on the encoder decoder architecture of SegNet and pairwisely fuse the convolutional features generated in the encoder network and in the decoder network at the same scale.)