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…
A generative speech model for daily dialogue.
Real-time face swap for PC streaming or video calls
A generative world for general-purpose robotics & embodied AI learning.
PyTorch implementations of Generative Adversarial Networks.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
Anomaly detection related books, papers, videos, and toolboxes
A python library for user-friendly forecasting and anomaly detection on time series.
Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
BoxMOT: Pluggable SOTA multi-object tracking modules modules for segmentation, object detection and pose estimation models
Distributed Asynchronous Hyperparameter Optimization in Python
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
Data on COVID-19 (coronavirus) cases, deaths, hospitalizations, tests • All countries • Updated daily by Our World in Data
Uplift modeling and causal inference with machine learning algorithms
Count the MACs / FLOPs of your PyTorch model.
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Torchreid: Deep learning person re-identification in PyTorch.
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
The state-of-the-art image restoration model without nonlinear activation functions.
Optical character recognition for Japanese text, with the main focus being Japanese manga
Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.