Rotate Yolov5 with adjustments to enable rotate prediction boxes

This repository is based on Ultralytics/yolov5, with adjustments to enable rotate prediction boxes. The codes are based on Ultralytics/yolov5, and several functions are added and modified to enable rotate prediction boxes. The modifications compared with Ultralytics/yolov5 and their brief descriptions are summarized below: data/rotate_ucas.yaml : Exemplar UCAS-AOD dataset to test the effects of rotate boxes data/images/UCAS-AOD : For the inference of rotate-yolov5s-ucas.pt models/common.py : 3.1. class Rotate_NMS : Non-Maximum Suppression (NMS) module for Rotate Boxes 3.2. class Rotate_AutoShape : Rotate […]

Read more

Simple implementation of Mobile-Former on Pytorch

Simple-implementation-of-Mobile-Former At present, only the model but no trained. There may be some bug in the code, and some details may be different from the original paper, if you are interested in this, welcome to discuss. Add: CutUp,MixUp,RandomErasing,SyncBatchNorm for DDP train Inference: paper:https://arxiv.org/pdf/2108.05895.pdf https://github.com/xiaolai-sqlai/mobilenetv3 https://github.com/lucidrains/vit-pytorch https://github.com/Islanna/DynamicReLU GitHub https://github.com/ACheun9/Pytorch-implementation-of-Mobile-Former    

Read more

A PyTorch implementation of Protagonist Antagonist Induced Regret Environment Design

This codebase provides a PyTorch implementation of Protagonist Antagonist Induced Regret Environment Design (PAIRED), which was first introduced in “Emergent Complexity and Zero-Shot Transfer via Unsupervised Environment Design” (Dennis et al, 2020). This implementation comes integrated with custom adversarial maze environments based on MiniGrid environment (Chevalier-Boisvert et al, 2018), as used in Dennis et al, 2020. Unsupervised environment design (UED) methods propose a curriculum of tasks or environment instances (levels) that aims to foster more sample efficient learning and robust […]

Read more

GAN encoders in PyTorch that could match PGGAN, StyleGAN v1/v2, and BigGAN

MTV-TSA MTV-TSA: Adaptable GAN Encoders for Image Reconstruction via Multi-type Latent Vectors with Two-scale Attentions. This is the official code release for “Adaptable GAN Encoders for Image Reconstruction via Multi-type Latent Vectors with Two-scale Attentions”. The code contains a set of encoders that match pre-trained GANs (PGGAN, StyleGANv1, StyleGANv2, BigGAN) via multi-scale vectors with two-scale attentions. Usage training encoder with center attentions (align image) python E_align.py training encoder with Gram-based attentions (misalign image) python E_mis_align.py embedding real images to latent […]

Read more

Simple torch module implementation of Alias-Free GAN

Simple torch module implementation of Alias-Free GAN. This repository including Note: Since this repository is unofficial, filter and upsample could be different with official implementation. Note: 2d lowpass filter is applying sinc instead of jinc (first order Bessel function of the first kind) in paper Requirements Due to torch.kaiser_window and torch.i0 are implemeted after 1.7.0, our repository need torch>=1.7.0. TODO [x] 2d sinc filter [x] 2d resample [x] devide 1d and 2d modules [ ] pip packaging Test results 1d […]

Read more

Discovery Header Bug Bounty to DoD with python

Did you know that DoD accepts server headers? 😲 (example: apache”version” , php”version”) ? In this code it is possible to extract all headers from the URLS.Tracking versions and being able to report as cwe-200 on hackerone. the 200dds file is an example: You can put your list of treated URLS. Install dependencies git clone https://github.com/KingOfBugbounty/Discovery-Header-Bug-Bounty.git cd Discovery-Header-Bug-Bounty pip install -r requirements.txt python3 searchHEADER.py -h usage: searchHEADER.py [-h] help positional arguments: help Run to code = python3 searchHEADER.py FileToUrls optional […]

Read more

Evidence enables analysts to deliver a polished business intelligence system using SQL

Business Intelligence for Modern Data Teams Evidence enables analysts to deliver a polished business intelligence system using SQL and markdown. It offers a modern development workflow for analysts and a polished user experience for decision-makers. An Evidence project is a collection of markdown documents. Whenever you write SQL queries in those documents, Evidence runs that SQL against your data warehouse. You can reference the results of those queries directly in your markdown document’s text, or you can use them to […]

Read more

A minimal Python library to draw customized maps from OpenStreetMap data

prettymaps A minimal Python library to draw customized maps from OpenStreetMap data. Based on osmnx, matplotlib, shapely and vsketch libraries. Google Colaboratory Demo Installation Install with $ pip install git+https://github.com/abey79/vsketch#egg=vsketch $ pip install git+https://github.com/marceloprates/prettymaps.git # Init matplotlib figure fig, ax = plt.subplots(figsize = (12, 12), constrained_layout = True) backup = plot( # Address: ‘Praça Ferreira do Amaral, Macau’, # Plot geometries in a circle of radius: radius = 1100, # Matplotlib axis ax = ax, # Which OpenStreetMap layers to […]

Read more

A command-line photo search tool based on the awesome OpenAI’s CLIP neural network

rclip is a command-line photo search tool based on the awesome OpenAI’s CLIP neural network. Installation Currently, pre-built distributable is available only for Linux x86_64. Download the AppImage from the latest release. Execute following commands: $ chmod +x $ sudo mv /usr/local/bin/rclip Usage $ cd photos && rclip “search query” How do I preview the results? The command from below will open top-5 results for “kitty” in your default image viewer. For this to work, you’ll have to index the […]

Read more

Blockchain-Enabled IoT Sensor Framework that uses Augmented Reality and Artificial Intelligence

Arduino + Raspberry Pi + Unity3D + Cloud + Hyperledger Our Mission: Keep it simple, leave no one behind. Blockchain-Enabled Smart Sensor Framework using Augmented Reality. Blockchain-Enabled Smart Sensor Framework using Augmented Reality. Extended Realities for IoT. View Sensor data in 3D This project was built to help developers create extended realities that communicate with Arduino and require the security of blockchain decentralization. (__/)                                    /)__/) (=’ .’) / COLLABORATION (‘. ‘=) o(_(“)(“)                          (“)(“)_)o Instructions Connect Sensors to Unity3D […]

Read more
1 496 497 498 499 500 928