Tim-Wory's repositories
TCN
Sequence modeling benchmarks and temporal convolutional networks
feature-engineering-handbook
A practical feature engineering handbook
keras-tcn
Keras Temporal Convolutional Network.
Neural-Net-with-Financial-Time-Series-Data
This solution presents an accessible, non-trivial example of machine learning (Deep learning) with financial time series using TensorFlow
Underwater_detection
2020年全国水下机器人(湛江)大赛
Dehaze-GAN
TensorFlow code for Single Image Haze Removal using a Generative Adversarial Network
LSTM-Human-Activity-Recognition
Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier
self-supervised_learning_sketch
self-supervised learning, deep learning, representation learning, RotNet, temporal convolutional network(TCN), deformation transformation, sketch pre-train, sketch classification, sketch retrieval, free-hand sketch, official code of paper "Deep Self-Supervised Representation Learning for Free-Hand Sketch"
dehaze_underwater_image
dehaze_underwater_image
traffic_sign_recognition
Traffic Sign recognition using SVM, and CNN with HOG
human-detector
Human Detection using HOG-Linear SVM in Python
UWGAN_UIE
Source code for UWGAN: Underwater GAN for Real-world Underwater Color Restoration and Dehazing
HOG-Pedestrian-Detector
MATLAB implementation of a basic HOG + SVM pedestrian detector.
traffic_sign_detection
A traffic sign detector using cascade SVM and OpenCV
Real-time-Traffic-light-detection-tool
A real time traffic light recognition tool chain using HOG+SVM and CNN,which localises ansd predicst the class of the TL object.
traffic-sign-recognition
Traffic Sign Detection, Color Threshold, Bounding Box, HOG features, SVM
GTSRB-Traffic-Sign-Recognition-Part2
Traffic Sign Recognition Project Part II focusing on RandomForest and SVM. HOG features are introduced. Combinations of feature extraction and feature selection/PCA are analyzed.
lstms.pth
PyTorch implementations of LSTM Variants (Dropout + Layer Norm)
Image-and-Video-Dehazing
This repository will consist of python code for image and video dehazing of underwater and foggy images
LSTM-FCN
Codebase for the paper LSTM Fully Convolutional Networks for Time Series Classification
deep-learning
personal practice(个人练习,实现了深度学习中的一些算法,包括:四种初始化方法(zero initialize, random initialize, xavier initialize, he initialize),深度神经网络,正则化,dropout, 三种梯度下降方法(BGD, SGD, mini-batch),六种优化算法(momentum、nesterov momentum、Adagrad、Adadelta、RMSprop、Adam),梯度检验、batch normalization)、RNN
Traffic-Sign-Detection-1
Traffic signs detection and classification in real time
TCN_classification
TCN时间卷积序列 支持tensorflow-serving部署 .tf.data tf.estimator
traffic-sign-detection
traffic sign detection with HOG feature and SVM model
HOG_SVM
使用HOG+SVM进行图像分类
Easy_HMM
A easy HMM program written with Python, including the full codes of training, prediction and decoding.
Underwater-Image-Enhancement-by-Wavelength-Compensation-and-Dehazing
ACQUIRING clear images in underwater environments is an important issue in ocean engineering. The quality of underwater images plays a pivotal role in scientific missions such as monitoring sea life, taking census of populations, and assessing geological or biological environments. Capturing images underwater is challenging, mostly due to haze caused by light that is reflected from a surface and is deflected and scattered by water particles, and colour change due to varying degrees of light attenuation for different wavelengths. Light scattering and colour change result in contrast loss and colour deviation in images acquired underwater.