Deep Learning, NLP, NMT, AI, ML
deepstream python play rtsp h264 n gstreamer python play rtsp h264 and h265 n common=> deepstream_python_apps=>apps n dstest3_pgie_config.txt ： test pgie n deepstream_rtsp_h264.py ：play one rtsp h264 n deepstream_rtsps_h264.py ：play Multiple rtsp h264 n deepstream_videos_h264.py ：play Multiple video h264 n gstreamer_test_h264.py ：play one rtsp h264 n gstreamer_test_h265.py ：play one rtsp h265 n GitHub View Github
Read more
Covid-polygraph, a set of Machine Learning-driven fact-checking tools that aim to address the issue of misleading information related to COVID-19. Project is extended based on our CS3244 Team Projectand more on code reference and reuse can be found in the Offline Training Pipeline Repository. How to run the backend code To run the code, use Docker: docker build . -t covid-polygraph:latest Afterwards, you can start the backend locally using the docker image built. For our team, we deploy this image […]
Read more
Visrl (pronounced “visceral”) is a simple wrapper to analyse and visualise reinforcement learning agents’ behaviour in the environment. Reinforcement learning requires a lot of overhead code to inspect an agent’s behaviour visually, typically through env.render(). Visrl allows users to easily intervene and switch between agent control and human control, and allows inserting a breakpoint in the game state to pause only at a relevant state of interest. Features Set action hotkeys Human intervention: Take actions 1 step at a time […]
Read more
Telegram bot to stream videos in telegram voicechat for both groups and channels. Supports live steams, YouTube videos and telegram media. Variables See Variables Pre Requisites Recommended Optional Vars DATABASE_URI: MongoDB database Url, get from mongodb. This is an optional var, but it is recomonded to use this to experiance the full features. HEROKU_API_KEY: Your heroku api key. Get one from here HEROKU_APP_NAME: Your heroku apps name. FILTERS: Filter the search for channel play. Channel play means you can play […]
Read more
This repository contains the code needed to train Mega-NeRF models and generate the sparse voxel octrees used by the Mega-NeRF-Dynamic viewer. The codebase for the Mega-NeRF-Dynamic viewer can be found here. Note: This is a preliminary release and there may still be outstanding bugs. Citation @misc{turki2021meganerf, title={Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs}, author={Haithem Turki and Deva Ramanan and Mahadev Satyanarayanan}, year={2021}, eprint={2112.10703}, archivePrefix={arXiv}, primaryClass={cs.CV} } Demo Setup
Read more
A timetable optimsier which uses an evolutionary algorithm to “breed” a timetable suited to your needs. Try it out here! Inspiration Planning the best fit timetable to suit our needs can be an absolute nightmare. Different sets of modules can result in a seemingly limitless combinations of timetable. Comparing and choosing the best timetable can take hours or even days. The struggle is real Having chanced upon an article on genetic algorithm, we thought that this would be the best […]
Read more
These are ghidra scripts to help with 3ds reverse engineering. Features: Labels, comments (when inlined), and bookmarks svc use Labels service handles, given ctr::srv::GetServiceHandleDirect Labels IPC functions and uses handles to better identify functions Adds ThreadLocalStorage and types thread local storage Renames thread local storage to ‘tls’ These have been built over time for my personal use as needs came up, so results may vary and improvements can be made. If you run into a situation where these don’t work […]
Read more