Fisher's repositories
CSDN-code-link
由于CSDN博客里面不能直接上代码链接,涉嫌营销推广,因此建一个github仓库用于整理这些代码链接
Yolov5-instance-seg-tensorrt
fish-kong/Yolov5-Instance-Seg-Tensorrt-CPP
Yolov8-instance-seg-tensorrt
based on the yolov8,provide pt-onnx-tensorrt transcode and infer code by c++
face-recognize-by-comera
1、结合opencv,利用特征提取方法(LDA LBP PCA)进行特征提取建立模型库;2、利用电脑摄像头进行拍照,每隔3秒提取一个正面照进行特征提取,然后与模型库中的样本进行余弦距离相似度计算,实现人脸匹配识别
-rnn-each-types-of-rnn-for-regression
利用各种循环网络进行回归拟合,包括rnn,lstm,nlstm,bilstm
texture-classification-based-on-BPNN-and-dictionary
代码主要包括:1。特征提取 首先对文本信息进行分词处理,采用基于字符串匹配的方法: 假如一段叫:李二狗就是一个** 基于匹配的方法就是依次截取一到多个词,并与字典库进行匹配。如二狗,如果匹配到字典中有这个词,则将其分为一个词;当取到“狗就”,发现字典中没有与之匹配的,则说明这个不是一个词语,进行顺序操作,最优将这段话分为:李 二狗 就是 一个 **。 2. 得到分词后的文本之后,就是转换成数字编码,因此电脑没办法识别汉字。这一部分叫特征表示,即用数字的方式表示中文文本,采用的方法是基于词带模型的特征表示: 词带就是字典--程序中那个dictionary.mat。我们将分词处理之后的文本中的每一个词语,分别与字典中的词进行匹配,只要出现过就为1,否则为0。 如 字典中的词含有:李 周 吴 郑 王 他妈的 就是 大 ** 一个 三炮 也是 瓜娃子,一共13词(当然正常的词典都是上万个词),将1中得到的词语与之匹配,则李二狗就是一个**对应的数字编码就应该是 1 0 0 0 0 0 1 0 1 1 0 0 0 3,通过2我们将文本表示成了数字,但是这样的表示通常都是稀疏的(因为一般字典都含有上万个词,所以得到的数字表示大部分都是0),为此我们利用降维方法,消除掉这些冗余特征。这里我们采用的PCA(主成分分析)进行降维,并降至15维。 4. 文本分类,采用的就是bp网络 代码修改的地方不多,主要就是超参数的选择,(1)如pca的降维数,维数过高,包含冗余数据,过低又会删除掉重要信息。(2)bp网络结构的调整,如隐含层节点数,学习率,等
objective-detection
利用LBP进行特征提取,SVM进行2分类器建模;利用滑动窗口实现目标检测
dbn-tool-box
dbn tool box deep belief network tool box
supervised-LPP
supervised LPP, This algorithm used kernel algorithm and label date when calculate the Euclidean distance D , ,by contract, another supervised LPP used label-data when calculate the weights matrix
Recurring-PCA-LPP-papers
2 days later, found a interesting paper. this paper combined PCA with LPP, and formed a comprehensive algorithm for data dimension deduction. in CNKI
CVPR2023-Papers-with-Code
CVPR 2023 论文和开源项目合集
PyTorch-GAN
PyTorch implementations of Generative Adversarial Networks.
PyTorch-Networks
Pytorch implementation of cnn network
Rotation-box-dimension-tool-and-dimension-file-adjustment
Rotation box dimension tool and dimension file adjustment
Transfer-Learning-for-Fault-Diagnosis
This repository is for the transfer learning or domain adaptive with fault diagnosis.
awesome-unsupervised-anomaly-detection
A Curated List of Awesome Unsupervised Anomaly Detection on MVTec AD Dataset
Awesome-Visual-Transformer
Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)
CycleGAN_1dCNN
Tensorflow implementation of a CycleGAN with a 1D Convolutional Neural Network and Gated units with options for the residual connections, dilations and a PostNet.
DOTA-DOAI
This repo is the codebase for our team to participate in DOTA related competitions, including rotation and horizontal detection.
ETDataset
The Electricity Transformer dataset is collected to support the further investigation on the long sequence forecasting problem.
GAN-AD
We used generative adversarial networks (GANs) to do anomaly detection for time series data.
gaussian-ad-mvtec
Code underlying our publication "Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection" at ICPR2020
learnopencv
Learn OpenCV : C++ and Python Examples
P-Net_Mvtec_AD
Main P-Net(ECCV 2020) on Mvtec dataset
Rotating-machine-fault-data-set
Open rotating mechanical fault datasets (开源旋转机械故障数据集整理)
tensorrtx
Implementation of popular deep learning networks with TensorRT network definition API
yolov5-dnn-cpp-python-v2
用opencv的dnn模块做yolov5目标检测,包含C++和Python两个版本的程序,优化后的