JarvisUSTC

Jarvis's repositories

VectorNet

A Simple Implementation of VectorNet Model

Language:Python18 2 1

This is an accurate implementation for IoU loss between two rotated polygons. This algorithm is accurate and differential, but there is no support for cuda now. In https://github.com/lilanxiao/Rotated_IoU, the implementation is fast but inaccua

Language:Python17 2 1

RotatedObjectDetectionEvaluation

This repo is evaluation codes for rotated object detection which uses polygon representation (x1,y1,x2,y2...,x4,y4) of bounding box, mainly based on Deformable DETR.

Language:PythonMIT700

Language-Enhanced-CLIP-For-Multi-label-Image-Recognition

3rd Place, Visual Prompt Tuning Challenge @ CVPR 2023 HIT Workshop (2023)

Language:PythonMIT500

2019ComputerNetwork

homework,lab,and some others

Language:C++MIT1 20

2019Web

Language:Python1 20

Awesome-Hierarchical-Document-Structure-Analysis

100

Awesome-Transformer-in-CV

A Survey on Transformer in CV.

MIT100

DARDet

Language:PythonApache-2.0100

image_style_transfer

Gatys_Image_Style_Transfer_CVPR_2016_paper

Language:Python1 20

Tiny_Python_Interpreter

A simple python interpreter implemented by yacc and lex

Language:YaccMIT1 10

2020SoftwareEngineering

Language:JavaScript020

awesome-wechat-weapp

微信小程序开发资源汇总 :100:

GPL-3.0010

BankManage

2020Spring Database Lab3/A Information Manage System Implemented by django+bootstrap4+mysql

Language:JavaScript020

ckpt_for_competition

000

ConditionalDETR

This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)

Apache-2.0000

DeepLearning-500-questions

GPL-3.0000

Deformable-DETR

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Language:PythonApache-2.0010

DINO

Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

000

DL-Notes-for-Interview

deep learning/ machine learning

010

DPED

Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks

Language:Python010

FightLordlocal

Reinforcement learning

Language:Python000

hiertext

The HierText dataset contains ~12k images from the Open Images dataset v6 with large amount of text entities. We provide word, line and paragraph level annotations.

Language:Jupyter NotebookCC-BY-SA-4.0000