A modular framework for neural networks with Euclidean symmetry

Zero-shot Image-to-Image Translation [SIGGRAPH 2023]

Configs and boilerplates for Label Studio's Machine Learning backend

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

FlagGems is an operator library for large language models implemented in the Triton Language.

Code for "Neural 3D Reconstruction in the Wild", SIGGRAPH 2022 (Conference Proceedings)

Python examples on how to use GStreamer within OpenCV. Now with GPU support! 🔥🔥🔥

Perceptual Metrics of Audio - perceptually relevant loss function. DPAM and CDPAM

[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.

Can CNNs transliterate Pinyin into Chinese characters correctly?

Somiao Pinyin: Train your own Chinese Input Method with Seq2seq Model 搜喵拼音输入法

A package to download ECMWF open data

[NeurIPS 2022, T-PAMI 2023] Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

A raytracer written in PyTorch (raynet?)

Audio-Visual Speech Separation with Cross-Modal Consistency

facenet人脸检测与识别系统

This is a toolbox for Deep Active Learning, an extension from previous work https://github.com/ej0cl6/deep-active-learning (DeepAL toolbox).

Tiny optimized Stable-diffusion that can run on GPUs with just 1GB of VRAM. (Beta)

[NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models

Practical low-rank gradient compression for distributed optimization: https://arxiv.org/abs/1905.13727

人民日报爬虫（Python）

Implementation of Post-training Quantization on Diffusion Models (CVPR 2023)

Official code for the paper "Visual Speech Enhancement Without A Real Visual Stream" published at WACV 2021

Python codes for Lite Audio-Visual Speech Enhancement.

Implementation of DiffusionOverDiffusion architecture presented in NUWA-XL in a form of ControlNet-like module on top of ModelScope text2video model for extremely long video generation.

北邮王晓茹老师数据挖掘与数据仓库文本数据的分类与分析实验

Wasserstein Adversarial Active Learning

北邮《数据挖掘》课程项目

Automatic detection of multi-speaker fragments with high time resolution