资源列表
Embedded-Image-Processing-with
- 2. Structure and Organization of the Book Prerequisites Conventions and Nomenclature CD-ROM The Representation of Digital Images DSP Chips and Image Processing Useful Internet Resources 2 3 4 6 9 10 13 ls 15 . The TMS320C6000 Line of
01GPOPs
- 最优控制理论的成套算法，其中有使用安装说明。(A complete set of algorithms for optimal control theory.)
ShowMapTheShortestRoute
- 根据一副地图，在地图上任意点击两地点，可画出两点的最短距离路线。对要熟悉MFC用法及最短路算法的初学者有很大帮助。-According to a map, click on the map on the two locations, you can draw two points of the shortest distance route. To be familiar with MFC usage and the shortest path algorithm for beginners a
MATLAB
- 冈萨雷斯数字图像处理MATLAB版 中文版.rar-Gonzalez Digital Image Processing MATLAB version of the Chinese version. Rar
3dLOF
- 三维点云的LOF算法，可以计算各点的LOF值，进而识别离群点。带入用户自己的TXT形式的点云文件即可。(The LOF algorithm of 3D point cloud can calculate the LOF value of each point, and then identify outliers. Bring the user's own TXT form of point cloud file.)
TensorFlow
- 这是香港科技大学的tensorflow课程，对于深度学习入门很有帮助(This is the tensorflow course at the Hong Kong University Science & Technology, which is helpful for the introduction of deep learning)
F16 simulation
- to simulate dynamic motion of F16
F16 simulation
- T0 SIMULATE DYNAMIC MOTION OF F16
Introduction-to-Algorithms
- 有算法导论英文版和中文版，现代计算机常用数据结构和算法-With Introduction to Algorithms, English and Chinese, modern computer data structures and algorithms commonly used
01-课件
- 吴恩达 人工智能课程课件讲义，含已出的4个课程(The Wu Enda artificial intelligence course lecture notes, including the 4 courses already out)
SceneTextCNN_demo.tar
- 端至端卷积神经网络的文字识别,代码演示包. 它包含我们的论文中使用的所有主要组成部分: kmeans无监督特征学习 + 卷积神经网络(CNN)-This is a demo package of the code we used for our paper, "End-to-End Text Recognition with Convolutional Neural Networks", T. Wang, D. Wu, A. Coates, A. Ng, in ICPR 2012.
Keras快速上手：基于Python的深度学习实战
- 该书理论和实践相结合，介绍了当前深度学习应用的几个主要框架和应用方向，实用性强，内容紧凑。基于Keras这个高度抽象的深度学习环境，全书强调快速构造深度学习模型和应用于实际业务，因此特别适合深度学习实践者和入门者学习，是一本必不可少的参考书。(The book combines theory and practice to introduce several main frameworks and application directions of current deep learning a