stephen-hao Goto Github PK

adversarial-example-attack-and-defense

This repository contains the implementation of three adversarial example attack methods FGSM, IFGSM, MI-FGSM and one Distillation as defense against all attacks using MNIST dataset.

awesome_cv_research

bank-card-number-identification

基于openCV&Tensorflow的银行卡号识别

chineseocr

yolo3+ocr

circleloss

Pytorch implementation of the paper "Circle Loss: A Unified Perspective of Pair Similarity Optimization"

circleloss.pytorch

Examples of playing with Circle Loss from the paper "Circle Loss: A Unified Perspective of Pair Similarity Optimization", CVPR 2020.

contrastive-clustering

Code for the paper "Contrastive Clustering" (AAAI 2021)

deep-learning

深度学习的实战项目

deephash-pytorch

Implementation of Some Deep Hash Algorithms, Including DPSH、DSH、DHN、HashNet、DSDH、DTSH、DFH、GreedyHash、CSQ.

dive-into-dl-pytorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

effcientnetv2

EfficientNetV2 implementation using PyTorch

faceai

一款入门级的人脸、视频、文字检测以及识别的项目.

facerecognition

Face recognition using triplet loss, implementing FaceNet with pytorch.人脸识别项目，提供一个小型数据集用作验证，使用三元组损失函数(Triplet loss)提升准确率和泛化能力，对FaceNet进行了一种实现。

facila-landmarks-challenge.github.io

gaitset

A flexible, effective and fast cross-view gait recognition network

generate_handwritten_number

Generate handwritten numbers from 1 to 9 and make handwritten number database / 生成手写体数字1-9并构建数据集

hourglass-facekeypoints-detection

face keypoints deteciton based on stackedhourglass

im2txt_chinese

深度学习实现图像中文描述

image-caption

Image caption in Chinese 图像中文描述

image-captioning

Implementation of 'X-Linear Attention Networks for Image Captioning' [CVPR 2020]

imagecaptioning.pytorch

Image captioning codebase in pytorch(self-critical training and more advanced features are under my self-critical.pytorch repository (worth checking).)

imagenet-tsne

python port of karpathy t-SNE code

imagenet21k

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(2021) paper

leetcode-master

LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

medmnist

pip install medmnist: 18 MNIST-like Datasets for 2D and 3D Biomedical Image Classification

nanodet

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

ocr_densenet

第一届西安交通大学人工智能实践大赛（2018AI实践大赛--图片文字识别）第一名；仅采用densenet识别图中文字

one-to-infinity

学习的一些小整理

paddleocr

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）

prepare_detection_dataset

convert dataset to coco/voc format