-
UDSMProt-master
说明： 基于深度学习的深度神经网络融合的蛋白质预测位点算法(Protein prediction site algorithm based on deep learning and deep neural network fusion)
- 2020-12-17 21:52:57下载
- 积分：1
-
convert
用python将php数组通过正则表达式转换成javascript的字典，然后打印出来(Php array by regular expression in python to convert javascript dictionary, and then print out)
- 2012-07-26 17:24:57下载
- 积分：1
-
CNN
说明： python 经典CNN模型。包括VGG resnet等(python classic cnn deep learning)
- 2020-10-11 17:49:19下载
- 积分：1
-
online_fengci
说明： 对现存的主流分词方法进行了分析和比较，对前人的成果和经验进行了研究和改进,设计实现了一个基于词典和统计方法的在线中文分词系统。本文系统使用了基于一种主流分词方法的经典算法,双向最大匹配法。这种方法能够将正向最大匹配法得到的分词结果和逆向最大匹配法得到的结果进行比较，从而决定正确的分词方法。这类算法的优点是速度快，时间复杂度为O（n），实现简单。本系统为用户提供了一个中文分词的在线平台，有文本分词，输入分词内容，实时显示分词结果等功能可供使用，本系统在切词准确度和速度上的表现较为良好,基本完成了中文分词的工作,提供了较好的用户体验。本文系统的创新点在于，将python语言作为开发语言，并选择了较为热门的web框架Flask作为开发在线系统的框架，实现了一个在线中文分词系统。目的是方便用户进行分词，并实时观测结果。(This paper analyzes and compares the existing mainstream word segmentation methods, studies and improves the previous achievements and experiences, and designs and implements an online Chinese word segmentation system based on dictionary and statistical methods. In this paper, a classical algorithm based on a mainstream word segmentation method, bi-directional maximum matching method, is used. This method can compare the result of forward maximum matching method with that of reverse maximum matching method, so as to determine the correct segmentation method. This kind of algorithm has the advantages of high speed, O (n) time complexity and simple implementation.)
- 2020-06-11 15:10:29下载
- 积分：1
-
简单案例实现——利用SVM进行分类预测
实现一个简单的SVM案例，即鸢尾花分类，利用SVM对UCI的IRIS数据进行了分类预测。
- 2022-01-26 01:15:35下载
- 积分：1
-
rnn-from-scratch-master
RNN神经网络的应用和概念，RNN源代码和使用方法(You can find that the parameters `(W, U, V)` are shared in different time steps. And the output in each time step can be**softmax**. So you can use**cross entropy** loss as an error function and use some optimizing method (e.g. gradient descent) to calculate the optimized parameters `(W, U, V)`.
Let recap the equations of our RNN:
)
- 2016-05-27 09:34:46下载
- 积分：1
-
Unet-master2
CN对图像进行像素级的分类，从而解决了语义级别的图像分割（semantic segmentation）问题。与经典的CNN在卷积层之后使用全连接层得到固定长度的特征向量进行分类（全联接层＋softmax输出）不同，FCN可以接受任意尺寸的输入图像，采用反卷积层对最后一个卷积层的feature map进行上采样, 使它恢复到输入图像相同的尺寸，从而可以对每个像素都产生了一个预测, 同时保留了原始输入图像中的空间信息, 最后在上采样的特征图上进行逐像素分类。(CN classifies images at the pixel level, thus resolving the problem of semantic segmentation at the semantic level. Unlike classical CNN, which uses full-connection layer to get fixed-length feature vectors after convolution layer for classification (full-connection layer + soft Max output), FCN can accept any size of input image, and uses deconvolution layer to sample feature map of the last convolution layer to restore it to the same size of input image, so that each pixel can be generated. At the same time, the spatial information of the original input image is retained. Finally, the pixel-by-pixel classification is carried out on the feature map sampled above.)
- 2019-04-19 19:16:29下载
- 积分：1
-
PFLD-DEMO
说明： PFLD的python实现，用于人脸的关键点检测(Python implementation of PFLD for key point detection of human face)
- 2020-01-08 09:27:08下载
- 积分：1
-
高效爬虫代码
资源描述（最少50字。请完善应用资源描述，描述越详细，下载次数越多）
资源描述（最少50字。请完善应用资源描述，描述越详细，下载次数越多）
资源描述（最少50字。请完善应用资源描述，描述越详细，下载次数越多）
- 2023-04-21 16:55:03下载
- 积分：1
-
GA-DF2
说明： 利用GA遗传算法解决欺骗函数最优问题，具体问题描述如下，如有问题请与我联系(The deceptive functions are a family of functions in which there exists
low-order building blocks that do not combine to form the higher-order
building blocks. Here, a deceptive problem that consists of 25 copies of
the order-4 fully deceptive function DF2 is constructed for this paper.
DF2 can be described as follows:
f(0000)=28 f(0001)=26 f(0010)=24 f(0011)=18
f(0100)=22 f(0101)=6 f(0110)=14 f(0111)=0
f(1000)=20 f(1001)=12 f(1010)=10 f(1011)=2
f(1100)=8 f(1101)=4 f(1110)=6 f(1111)=30
This problem has a maximal function value of 750.)
- 2020-05-10 09:50:49下载
- 积分：1
