multipath Goto Github PK

efficient-neural-machine-translation

PhD thesis (updating) of Jiatao Gu from HKU

eg3d

epigraf

Official pytorch implementation of EpiGRAF

essg

essg

essg2

essg

estool

Evolution Strategies Tool

evolution-strategies-starter

Starter code for Evolution Strategies

fairseq-stable

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

faiss

A library for efficient similarity search and clustering of dense vectors.

fastpointtransformer

Official source code of Fast Point Transformer, CVPR 2022

fasttext_multilingual

Multilingual word vectors in 78 languages

fcgf

Fully Convolutional Geometric Features: Fast and accurate 3D features for registration and correspondence.

gangealing

Official PyTorch Implementation of GAN-Supervised Dense Visual Alignment (CVPR 2022 Oral, Best Paper Finalist)

ganhacks

starter from "How to Train a GAN?" at NIPS2016

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

groundhog

Library for implementing RNNs with Theano

guided-diffusion

gumbel

Gumbel softmax reparameterization for RNN decoding

hammer

An efficient toolkit for training deep models.

image-gpt

Pytorch Implementation of OpenAI's Image GPT, trained on MNIST and Fashion MNIST

image2edge

image to edge with pidinet

imaginaire-stable

NVIDIA's Deep Imagination Team's PyTorch Library

implicitautoencoder

improved_wgan_training

Code for reproducing experiments in "Improved Training of Wasserstein GANs"

install-opencv

shell scripts to install different version of OpenCV in different distributions of Linux

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

itchat

A complete and graceful API for Wechat. 微信个人号接口、微信机器人及命令行微信，三十行即可自定义个人号机器人。

iwae

Code to train Importance Weighted Autoencoders on MNIST and OMNIGLOT

joint_align

Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework

keras

Theano-based Deep Learning library (convnets, recurrent neural networks, and more).