lh77hl's Stars
ddbourgin/numpy-ml
Machine learning, in numpy
wiseodd/generative-models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
AccumulateMore/CV
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】
yuweihao/MambaOut
MambaOut: Do We Really Need Mamba for Vision?
xinychen/transdim
Machine learning for transportation data imputation and prediction.
MemorialCheng/deep-learning-from-scratch
《深度学习入门-基于Python的理论与实现》，包含源代码和高清PDF(带书签)；慕课网imooc《深度学习之神经网络(CNN-RNN-GAN)算法原理-实战》；《菜菜的机器学习sklearn》
wuwenjie1992/StarryDivineSky
精选了6K+项目，包括机器学习、深度学习、NLP、GNN、推荐系统、生物医药、机器视觉、前后端开发等内容。Selected more than 6000 projects, including machine learning, deep learning, NLP, GNN, recommendation system, biomedicine, machine vision, etc. Let more excellent projects be discovered by people. Continue to update! Welcome to star!
yangzhen0512/IntelligentOptimizationAlgorithms
This repository displays the demos of some Intelligent Optimization Algorithms, including SA (Simulated Annealing), GA (Genetic algorithm), PSO (Particle Swarm Optimizer) and so on. And some other algorithms will be appended in the future.
Tianfang-Zhang/awesome-infrared-small-targets
List of awesome infrared small targets detection methods!
arekavandi/Transformer-SOD
heihei12305/MOPSO
MOPSO及pso可编译运行matlab源码，及相关论文资源
deKeijzer/Multivariate-time-series-models-in-Keras
This repository contains a throughout explanation on how to create different deep learning models in Keras for multivariate (tabular) time series prediction.
bfshi/DGAM-Weakly-Supervised-Action-Localization
Code for our paper "Weakly-Supervised Action Localization by Generative Attention Modeling" (CVPR2020)
williamgilpin/fnn
Embed strange attractors using a regularizer for autoencoders
zhiyongc/GRU-D
Gated Recurrent Unit with a Decay mechanism for Multivariate Time Series with Missing Values
DrJZhou/Black-Swan
KDD CUP 2017
MrinmoiHossain/Udacity-Deep-Learning-Nanodegree
The course is contained knowledge that are useful to work on deep learning as an engineer. Simple neural networks & training, CNN, Autoencoders and feature extraction, Transfer learning, RNN, LSTM, NLP, Data augmentation, GANs, Hyperparameter tuning, Model deployment and serving are included in the course.
YimianDai/DENTIST
543877815/neural-network-practise
慕课网上深度学习之神经网络（CNN RNN GAN）算法原理+实战练习的代码和部分数据
ArnaudFickinger/Attention_VAE
VAE with Attention Mechanism for a more powerful representation of interactions
0zean/MARS-Time-Series
Multivariate Adaptive Regression Splines for Time Series Prediction
gevaertlab/BetaVAEImputation
sclincha/xrce_msda_da_regularization
Regularized marginalized Stacked Denoising Autoencoders for Domain Adaptation
stephenzwj/SolarGAN
Missing data impuation GAN for solar data
kvfrans/latent-attention
Attention on the latent vector for a VAE
qzcwx/CEC2010SS-LSGO-Benchmarks-CPP
This is a fast and easy to use C++ implementation of benchmark set proposed in CEC2010 special session on Large-Scale Global Optmization
andymiller/DR-VAE
pytorch code for discriminatively regularized variational autoencoders
AryaAftab/Two-Steps-GVF-Snake-Model
Active contours, or snakes, are widely used in medical image processing applications, mainly to locate the desired area boundaries. Gradient vector flow (GVF) field, like other methods of calculating external force fields, is proposed to address ordinary snake models’ problems, such as poor convergence in indentations and low accuracy in segmentation of objects owned weak borders. These problems are most pronounced in high-noise images, such as ultrasound images. In order to solve the problems more, we utilized the generalized gradient vector flow snake model using minimal surface and two steps converging using both vector based normalization and component-based normalization with distinct controlling parameters on active contour. We adopt minimal surface function to address the problem of low segmentation accuracy in other conventional methods. We also use two steps converging using both vector-based and component-based normalization with distinct controlling parameters to improve the snake curve converging into long and thin indentations plus higher accuracy in noisy and meandering areas. The results obtained and compared with other methods show that the proposed active contour model not only can converge better into long and thin indentations, along with maintaining weak boundaries but also shows higher accuracy in segmentation of tortuous areas, especially in noisy images.
jcchao/KDD_CUP_2018
KDD CUP 2018
sauradip/GVF-SWT-Based-OCR
This is a Self Designed OCR , built implementing Gradient Vector Flow and Stroke Width Transform which can Identify any Marathon / Sports Bib Number