Stars
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
Efficient vision foundation models for high-resolution generation and perception.
Implementation of different kinds of Unet Models for Image Segmentation - Unet , RCNN-Unet, Attention Unet, RCNN-Attention Unet, Nested Unet
Audio processing by using pytorch 1D convolution network
A full Python implementation for real car surround view system
Fast PyTorch based DSP for audio and 1D signals
TensorRT implementation of Depth-Anything V1, V2
[ICCV 2023] Implicit Neural Representation for Cooperative Low-light Image Enhancement
Audio Source Separation Without Any Training Data.
MoSQITo is a unified and modular development framework of key sound quality metrics favoring reproducible science and efficient shared scripting among engineers, teachers and researchers community.
NVIDIA TensorRT deployment of Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data.
This project is the translation to python of the most important parameters in the field of Psychoacoustics based on the book of Zwicker and Fastl "Psychoacoustics Facts and Models".