ycyoon Goto Github PK

pytorch_face_landmark

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100 FPS landmark inference speed with SOTA face detector on CPU.

rl4lms

A modular RL library to fine-tune language models to human preferences

rnapipe

rppg-toolbox

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

selectivesearch

sinvoice

Sound wave communication on Android like chirp on iphone

skflow

Simplified interface for TensorFlow (mimicking Scikit Learn)

slf-rpm

Official PyTorch implementation of AAAI-22: Self-supervised Representation Learning Framework for Remote PhysiologicalMeasurement using Spatiotemporal Augmentation Loss (SLF-RPM)

tadaconv

[ICLR 2022] TAda! Temporally-Adaptive Convolutions for Video Understanding. This codebase provides solutions for video classification, video representation learning and temporal detection.

tensorflow-tutorials

텐서플로우를 기초부터 응용까지 단계별로 연습할 수 있는 소스 코드를 제공합니다

tensorpack

A Neural Net Training Interface on TensorFlow

tracking-with-darkflow

Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow

trl

Train transformer language models with reinforcement learning.

udapi-python

Python framework for processing Universal Dependencies data

video-llama

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

video-swin-transformer

This is an official implementation for "Video Swin Transformers".

visual-embedding

Data & source code for the visual embedding model

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

vundle.vim

Vundle, the plug-in manager for Vim

word2vec

This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.

xlnet

XLNet: Generalized Autoregressive Pretraining for Language Understanding

ycyoon.github.io

A beautiful, simple, clean, and responsive Jekyll theme for academics

youtube-dl

Command-line program to download videos from YouTube.com and other video sites