Detection

A simple and extensible object detection evaluator in COCO style

Features Extensible user interfaces to deal with different data formats. Support customized evaluation breakdowns, e.g., object size in COCO, difficulty in KITTI, velocity and range in Waymo. Interface for general matching scores, e.g. 2D IoU, 3D rotated IoU, center distance. Support widely-used metrics like AP, AR and customized metrics like average regression errors, average IoUs, etc. Purely based on Python, easy to develop your customized metrics. Installation pip install treelib Clone this repo and run pip install . in the […]

Read more
Scripts

POC script for Malware Hunting over the WWW

POC script for Malware Hunting over the WWW To start with Malware Hunting, execute: python3 ./lovac.py. The script will start looking for random domain names, download first page to ./lovac_download/ folder and parse interesting strings to the ./lovac_output/ folder. After the tool is done, you can analyze output files manually and run the antivirus scan on download folder. The tool will save current status of discovery process in ./lovac_discovered.txt and ./lovac_tried.txt files. Discover “co.rs” domains, with minimum length 2 and […]

Read more
MediaPipe

Mediapipe Face Mesh with python

Here -> https://github.com/k-m-irfan/simplified_mediapipe_face_landmarks, I tried to isolate and simplify face landmarks for selecting points around specific facial features (eyes, iris, eyebrows, lips, and face boundary). But there’s an easier way to do it. We can use the connections argument of the draw_landmarks function of drawing_utils. We can even manually list the points of interest here to make a mesh. For Lips: mp.solutions.face_mesh_connections.FACEMESH_LIPS Left Eye: mp.solutions.face_mesh_connections.FACEMESH_LEFT_EYE Left Iris: mp.solutions.face_mesh_connections.FACEMESH_LEFT_IRIS Left Eyebrow: mp.solutions.face_mesh_connections.FACEMESH_LEFT_EYEBROW Right Eye: mp.solutions.face_mesh_connections.FACEMESH_RIGHT_EYE Right Iris: mp.solutions.face_mesh_connections.FACEMESH_RIGHT_IRIS Right Eyebrow: mp.solutions.face_mesh_connections.FACEMESH_RIGHT_EYEBROW […]

Read more
POC

A lightweight, flexible and novel open source poc verification framework

中文 README pocsploit is a lightweight, flexible and novel open source poc verification framework Pain points of the POC framework in the market There are too many params, I don’t know how to get started, but only some of them are commonly used. YAML poc framework(like nuclei & xray) is not flexible enough. the conversion cost is very high when writing poc. Sometimes it’s hard when encountering non-http protocols. (only hex can be used) Sometimes POC has false positives, which […]

Read more
Emojis

Send dm when user react to emoji

Send dm when user react to message. ✅ Setup: – Put the token on config file. – Put the message id to listen react. – Put delay before dm. – Put your message. 👀 If you don’t have proxies, desactivate proxy option, or buy them from my shop :p    

Read more
SVG

Port any SVG image to Geometry Dash

Port any SVG image to Geometry Dash Made by Jaan#2897(mostly) and some code by camila314(converting svg to objects) Feel free to contact me How to run Install Python 3.7+ Download this repo Run python main.py Input some values Done 🙂 How it works It basically just uses gd.py to add objects/create a level with them and svgpathtools to actually make those objects. Special thanks GitHub View Github    

Read more
Calculator

A loan eligibility calculator aiming to reduce algorithmic biases

A loan eligibility calculator aiming to reduce algorithmic biases. Made for Hack the Globe 2022 by Team 32. This code acts as a framework which banks/lenders can use to build on and improve their own loan eligability algorith, in order to reduce biases towards those of lower income (which often includes many marginalised groups) by determining their eligability for a loan without the use of a credit score, and also makes them less riskier to lend to by offering more […]

Read more
Environment

OpenAI Gym style Wrapper for Multi-agent environment which made by Unity ML-Agents

OpenAI Gym style Wrapper for Multi-agent environment which made by Unity ML-Agents This wrapper is used in Logistics Environment (for MARL) You can use this wrapper to wrap user algorithm to make OpenAI gym style like this, from UnityGymWrapper5 import GymEnv env = GymEnv(…) obs = env.reset() next_obs, rewards, done, info = env.step(actions) This wrapper file detect information of your ML-Agent environment automately (number of agents, state of each agents, number of actions etc…) GitHub View Github    

Read more
Neural Network

Graph Neural Networks for User Identity Linkage

data/: contains the processed data. The dataset Douban-Weibo is provided by the PHD student Siyuan Chen. If you use the data, please cite the following paper. More details refer to INFUNE. @inproceedings{chen2020infune, title={A Novel Framework with Information Fusion and Neighborhood Enhancement for User Identity Linkage}, author={Chen, Siyuan and Wang, Jiahai and Du, Xin and Hu, Yanqing}, booktitle={24th European Conference on Artificial Intelligence (ECAI)}, pages={1754–1761}, year={2020} }    

Read more
1 … 185 186 187 188 189 … 928