YOLO

A drowsiness detection based on YOLOv5 implementation

This repository consists of a drowsiness detection based on YOLOv5 implementation. You can reach the base repo here 1. Prepared Custom Data Set A custom data set was prepared for this project. Videos were taken from 21 different people in scenarios that could happen while driving. Three different categories were discussed in these videos: normal, yawning and head position. Various light conditions and the use of glasses were taken into account. A total of 63 videos were obtained and labeling […]

Read more
Video

Comparison between Frechet Video Distance implementation from StyleGAN-V and the original paper

In this repo, we demonstrate that the FVD implementation from StyleGAN-V paper is equivalent to the original one when the videos are already loaded into memory and resized to a necessary resolution. The main difference of our FVD evaluation protocol from the paper is that we strictly specify how data should be processed, clips sampled, etc. The problem with the original implementation is that it does not handle: data processing: in which format videos are being stored (JPG/PNG directories of […]

Read more
hcaptcha

Hcapcha image collector for artificial intelligence

import hcollector, requests s = requests.session() # s.proxies.update({“http”: “proxy”, “https”: “proxy”}) # Proxies are recommended for bulk collection due to restrictions on requests hcollector.HcaptchaCollector(s, 5).collect(“site key”, “url”) # Ex. ‘4c672d35-0701-42b2-88c3-78380b0db560’, ‘discord.com’    

Read more
Dependency Injection

Experiments with dependency injection in pipeline steps

This is an experiment to understand if we can write data pipelines in a way that you declare the supporting services that each step required, similar to how FastAPI’s Dependencies function. The manner in which each dependencies would be resolved would depend on its runtime environment, thus supporting pipelines that could run locally or in a cloud-based environment. Additionally, each pipeline step should be able to inform cloud providers of its permission requirements when deployed. Design Interfaces Interfaces serve as […]

Read more
Scripts

Python source code, that helps you to check for all weights of a font which is hosted in a website

This is python source code, that helps you to check for all weights of a font which is hosted in a website. Read the instructions, to learn how to use it. Screenshot Instructions Downloas and install Termux from here Run codes below in Termux: pkg install python pip install requests termux-setup-storage cd /path/to/code python Font-Downloader.py In the first input, you need to enter the font file url that you’ve found, but without weight name and foemat name (this method will […]

Read more
Scripts

Rig Builder: An easy to use ui maker for python scripts. Mostly used in Maya rigging

Rig Builder is a flexible UI maker for python scripts. Mostly used in Maya rigging but can be adapted for any other purposes. How to run Add rigBuilder folder to your script path and run the following: import rigBuilder rigBuilder.mainWindow.show() File structure Name Description modules All modules in xml qss Dark style utils Utilities such as yapf for python formatting widgets Attribute widgets classes.py Definition of the two main classes: Attribute and Module editor.py Python code editor templateWidgets.py Widgets set […]

Read more
Monitor

Monitor New Processes Created On MacOS

Monitor New Processes Created On MacOS, Similar to https://github.com/DominicBreuker/pspy, and https://objective-see.com/products/utilities.html. No Dependencies Required. Why Needed to monitor jamf scripts commandline arguments on mac recently, jamf api keys were being used in jamf scripts that ran peroidically. Using process monitor gathered curl args and got creds which allowed full access to jamf server. Allowing privesc. BUT ProcessMonitor requires root access and pspy doesnt work on mac due to no /proc directory. also ps cannot really be rewritten as it wont […]

Read more
End-to-End

An end to end deep learning method Mcformer to utilize the customer clickstream data to predict the user purchase intention

This is an end to end deep learning method Mcformer to utilize the customer clickstream data to predict the user purchase intention. We aim to utilize the customer clickstream data to predict the customer purchase intention, the scenes as follows: The framework of Mcformer Introduction of Mcformer In order to deal with multi-dimension clickstream sequence data, we proposed an end-to-end deep learning model, named Multi-channel for purchase transformer (Mcformer), to predict the customers’ purchasing intention. Figure 1 shows the model […]

Read more
SSH

SSH self-spreading worm

SSH self-spreading worm This is self-spreading worm through SSH. Warning its ILLEGAL in most of countries. Educational uses only. It takes 4 steps. #Step 1 Scanning random ips with port 22 to check is there any SSH. It is done by nmap. #Step 2 Ips from step 1, which have already been verified, attacked by bruteforce. It is done by hydra. #Step 3 Credentials from step 2 needed to be verifed again, because hydra causes a lot of false positive […]

Read more
1 … 199 200 201 202 203 … 936