📚150+ Tensor/CUDA Cores Kernels, ⚡️flash-attention-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS 🎉🎉).

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Hackable and optimized Transformers building blocks, supporting a composable construction.

Let us control diffusion models!

Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)

Audio generation using diffusion models, in PyTorch.

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time

Contrastive Learning (SimCLR) for Human Activity Recognition

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

Deezer source separation library including pretrained models.

An example of time series augmentation methods with Keras

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

ffmpeg support on jetson nano

A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding). Translations: 🇺🇸 🇨🇳 🇯🇵 🇮🇹 🇰🇷 🇷🇺 🇧🇷 🇪🇸

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Digital Communication with Python

DISTRIBUTED SOURCE CODING USING SYNDROMES.

Audio super resolution using neural networks

Fitbit heart rate and accelerator data upload to a remote web server.

STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks

TweetScraper is a simple crawler/spider for Twitter Search without using API

Deepsense: a unified deep learning framework for time-series mobile sensing data processing.

AutoPhrase: Automated Phrase Mining from Massive Text Corpora