资源列表
Swin-Unet
- 而此前由 MSRA 提出的 Swin Transformer 正好作为视觉 Transformer 领域新的backbone。相较于 TransUNet,去掉CNN编码,用 Swin Transformer 来代替原先的 ViT,将 UNet 全部结构都换成 Swin Transformer。因而,基于 Swin Transformer 的Swin-UNet就应运而生。
AntSystem
- 一个较好的蚁群MATLAB程序,附地图。-In this M-file, the implemention of ACO Algorithm is given with the support of reference papers listed. You can easily use it as following command to see the pictures of result and the iterative playing course.
ANN2
- 关于人工神经网络的电子书,可以作为分析神经网络的基础介绍-E-book on artificial neural networks, neural networks can be used as the basis for introduction of
ga
- 遗传算法,就是ga,就是求最优问题,自己写的一个小程序-Genetic algorithm is ga, is seeking optimization problem, write a little program
xqsdk
- 一个VC6.0的象棋源代码,智能程度很高
gn
- 社区发现的经典算法 GN算法的java测试-Java test of the classical algorithm GN algorithm for community detection
ASTAR-IMPROVE
- A*算法改进,对图进行搜索,获得最短路径,含源代码和实验报告-A* algorithm improvements for searching the graph shortest path
svm
- 支持向量机一个很好的,较新的一个进行分析分析的软件-Recent advances in experimental methods have resulted in the generation of enormous volumes of data across the life sciences. Hence clustering and classification techniques that were once predominantly the domain of ecologis
transmitter_model_final
- 在BFSK发射机的基本部分是序言和数据输入电路。序言序列定位在每122位的数据包前一共有128位的数据包。序言的主要目的是协助接待,同时提供同步和数据包位。 数据输入电路主要由来自存储元件和卷积编码器与R = 1 / 2。因此,输入位必须被储存在一个临时内存,并在61位的存储区块分区。然后,卷积编码器,并增加了一倍位在邮件的末尾2位更多线索。阿多路可确保正确的序列,编码的比特之间的序言和选择,是传播到下一个阶段。 在下一阶段的发射器由两个直接器(DDS)数字合成器,以及一个用0和
genetic_algorithms
- 有时间约束的车辆数优化的C程序(遗传算法)-time constraint optimization of the number of vehicles in C (GA)
CNN_Hyperspectral_Classification-master
- 使用神经网络进行训练,对高光谱普图像进行分类(Using neural network to train and classify hyperspectral images)
王者趋势-EA
- 一次一单,每单都带止损止盈,不加仓,做单准确率高,平均能达到90%,真正做到稳定盈利,风险降到最低。(One order at a time, each order with stop loss and stop profit, no additional positions, high accuracy rate of order making, the average can reach 90%, truly achieve stable profit, risk reduction to
