a2819z

weight-selection

Faster-Diffusion

[NeurIPS 2024] Official implementation of "Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models"

big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

fastapi-best-practices

FastAPI Best Practices and Conventions we used at our startup

Misc-Cheatsheet

대학원 생활을 하며 사용하는 작고 소중한 코딩팁 (linux 명령어 등)

DenseDiffusion

Official Pytorch Implementation of DenseDiffusion (ICCV 2023)

machine-learning-interview

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

MLQuestions

Machine Learning and Computer Vision Engineer - Technical Interview Questions

Ready-For-Tech-Interview

💻 신입 개발자로서 지식을 쌓기 위해 공부하는 공간 👨‍💻

tech-interview-for-developer

👶🏻 신입 개발자 전공 지식 & 기술 면접 백과사전 📖

coding-interview

취업 준비를 위해 공부한 내용을 정리하는 레포

ai-tech-interview

👩‍💻👨‍💻 AI 엔지니어 기술 면접 스터디 (⭐️ 1k+)

Monodepth

PyTorch implementation of Unsupervised Monocular Depth Estimation with Left-Right Consistency

Min-SNR-Diffusion-Training

[ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy

RetNet

An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"

InstaFlow

:zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

StereoAlgorithms

Stereo Algorithms (Include:CREStereo,RAFT-Stereo,Hitnet,FastACVNet_plus,Stereo Transformers,RealtimeStereo,DistDepth) with TensorRT,ORT,OpenVINO

ONNX-FastACVNet-Depth-Estimation

Python scripts performing stereo depth estimation using the Fast-ACVNet model in ONNX.

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

cav-mae

Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder".

VALL-E-X

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

Resemblyzer

A python package to analyze and compare voices with deep learning

Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

deepspeech.pytorch

Speech Recognition using DeepSpeech2.

AudioLDM2

Text-to-Audio/Music Generation

TriAAN-VC

TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion

ResShift

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

InjectFusion_official