Stars
All Algorithms implemented in Python
The world's simplest facial recognition api for Python and the command line
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
OpenMMLab Detection Toolbox and Benchmark
Automatic headphone equalization from frequency responses
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
微信助手：1.每日定时给好友（女友）发送定制消息。2.机器人自动回复好友。3.群助手功能（例如：查询垃圾分类、天气、日历、电影实时票房、快递物流、PM2.5等）
Code for the paper Hybrid Spectrogram and Waveform Source Separation
Pytorch implementation of convolutional neural network visualization techniques
💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
🔥 2D and 3D Face alignment library build using pytorch
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
Count the MACs / FLOPs of your PyTorch model.
Muzic: Music Understanding and Generation with Artificial Intelligence
NVIDIA's Deep Imagination Team's PyTorch Library
Model summary in PyTorch similar to `model.summary()` in Keras
3D ResNets for Action Recognition (CVPR 2018)
StarGAN v2 - Official PyTorch Implementation (CVPR 2020)
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
Flops counter for neural networks in pytorch framework
An optimizer that trains as fast as Adam and as good as SGD.
Python library and CLI tool to interface with Google Translate's text-to-speech API
Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)
Codebase for Image Classification Research, written in PyTorch.
Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.
Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.
An end-to-end PyTorch framework for image and video classification
Versatile audio super resolution (any -> 48kHz) with AudioSR.