gavin666github Goto Github PK

pysot

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

python-opencv

pytorch-cpn

A PyTorch re-implementation of CPN (Cascaded Pyramid Network for Multi-Person Pose Estimation)

pytorch-cyclegan-and-pix2pix

Image-to-image translation in PyTorch (e.g., horse2zebra, edges2cats, and more)

pytorch-i3d

pytorch-mfnet

pytorch-yolov3

Minimal PyTorch implementation of YOLOv3

pytorchocr

基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

pytracking

Visual tracking library based on PyTorch.

realtime-fall-detection-for-rnn

Real-time ADLs and Fall Detection implement TensorFlow

reid-mgn

Reproduction of paper: Learning Discriminative Features with Multiple Granularities for Person Re-Identification

reid-survey

Deep Learning for Person Re-identification: A Survey and Outlook

retinex

rotationdetection

This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

rude-carnie

Age/Gender detection in Tensorflow

sdc

A scaled down version of the self-driving system using OpenCV. The system comprises of - • Raspberry Pi with a webcam and an ultrasonic sensor as inputs, ◦ Steering using move in sdcar.py ◦ Stop sign detection using houghcircles and colour intensities ◦ Front collision avoidance using an ultrasonic sensor • l298N motor controller • project structure: *sdcar.py is a combination of all the following *lane_lines.py: step1.take the webcam feed and apply the canny edge algorithm to detect the edges step2. detect the lines in an edged image using houghlines step3. average the lines according to the slope step4.making points using slope step5. return right, left, camera and central line *sensor.py: distance measurement using input and output pins *sign.py: *detection of circles in image using hough circles *if the dominant colour in a square region around the circle is red then it is stop sign. *if the dominant colour in a square region around the circle is blue then there are 5 cases left, right, forward, forward and right or forward and left for this: • make the 3 zones of square regions the right , left, upper(for forward) • if the right zone is white and the other two are blue then the sum of RGB colour intensities in the right zone will be obviously greater than the other two zones then the sign is right similarly for others. Note : sign.py will work on following type of sign:

segmentation_models

Segmentation models with pretrained backbones. Keras.

seu_lanedetect

shape_predictor_81_face_landmarks

Custom shape predictor model trained to find 81 facial feature landmarks given any image

shorttermloiteringdetection

Short term loitering detection implementations

skin-detector

用opencv写的一个人的皮肤检测器，里面封装了多种算法

smad-on-fire

Based on the detection of fire in videos, binocular stereo matching technology is used to determine the location of fire sources .

smart_construction

Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程！！！😆🚀

sngan_projection

GANs with spectral normalization and projection discriminator

spider_baidu_image

爬取百度图片 爬虫

srgan

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

srgan-tensorflow

Tensorflow implementation of the SRGAN algorithm for single image super-resolution

srgan_wasserstein

Apply Waseerstein GAN into SRGAN, a deep learning super resolution model

srmd-pytorch

A PyTorch Implementation of "Learning a Single Convolutional Super-Resolution Network for Multiple Degradations"

stereo-vision

This program has been developed as part of a project at the University of Karlsruhe in Germany. The final purpose of the algorithm is to measure the distance to an object by combining two webcams and use them as a Stereo Camera.