🌕 [BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-processing.
- exposure-correction
- low-light-enhance
- transformer-architecture
- transformer-models
Programs to process GoPro MP4 & Generic GPX/FIT files and create video dashboards & maps
- gopro
- gopro-camera
- ffmpeg
- ffmpeg-script
Switch manager is a centralised component to handle button pushes for your wireless switches. This includes anything passed through the event bus. The component relies on switch blueprints which is easily made to allow GUI configuration of your switches and their button pushes. This helps remove clutter from the automations.
Scholar All-In-One: A research infrastructure for AI agents
Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence
Asynchronous Methods for Deep Reinforcement Learning
Enable root SSH on BMW MGU head units (iDrive 7 / ID8 BDC3 / ID8 BCP) over ENET - flash the debug image, enroll, persistent SSH with no B7F8E5 DTC, and a unique per-car key.
- developer-mode
- idrive
- idrive7
- root
Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN using Tensorflow)
用PaddlePaddle和Tensorflow实现常用的深度学习算法
DeMoN: Depth and Motion Network
- structure-from-motion
- cnn
- cvpr
- depth
💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)
This tool allows you to perform OSINT and reconnaissance on an organisation or an individual. It allows one to search 1.4 Billion clear text credentials which was dumped as part of BreachCompilation leak. This database makes finding passwords faster and easier than ever before.
Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
100M tokens. Infinite compute. Lowest val loss wins.
Gaze Estimation using Deep Learning, a Tensorflow-based framework.
QKeras: a quantization deep learning library for Tensorflow Keras
- deep-learning
- quantization
- quantized-neural-networks
- hardware-acceleration
Face Detection | Recognition | Attendance
Rotational region detection based on Faster-RCNN.
SQLAlchemy integration with marshmallow
This component allows you to pull in the energy prices into Home-Assistant.
C3D is a modified version of BVLC tensorflow to support 3D ConvNets.
Allows logging in via Facebook, Yahoo, Gmail, Twitter and Openid
Physics-based Noise Modeling for Extreme Low-light Photography (CVPR 2020 Oral & TPAMI 2021)
Raspberry PI-TIMOLO ( PI-TImelapse, MOtion, LOwLight ) uses RPI picamera and OpenCV for Remote Headless Security Monitoring using Motion Tracking, Rclone Auto Sync files with remote storage services. Auto Twilight Transitions and Low Light Camera Settings. Panoramic images using PanTiltHat and More. This project is featured on GitHub Awesome software.
- opencv
- pi-camera
- python
- lowlight