multipath Goto Github PK

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

rnn

Recurrent Neural Network library for Torch7's nn

rq-vae-transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

rsm

Topic analysis using RSM or PVDM.

rwkv-lm

RWKV-2 is a RNN with transformer-level performance. It can be directly trained like a GPT transformer (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

score-entropy-discrete-diffusion

Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

seg-nmt

Search Engine Guided Non-Parametric Neural Machine Translation

seq2seq

A general-purpose encoder-decoder framework for Tensorflow

sgn-rl

Bypassing the Black-Box Operation with Evolutionary Synthetic Gradients

shapelab

shapenetrender_more_variation

A new shapenet rendering 2D image dataset that also contains deph map, normal map and albedo map.

sockeye

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

softras

Official project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"

spatiotemporalsegmentation

4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)

splatter-image

Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction'

squirrel

PyTorch implementation of Transformer-based Neural Machine Translation

stable-dreamfusion

A working implementation of text-to-3D dreamfusion, powered by stable diffusion.

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

stack-rnn

This is the code used for the paper "Inferring algorithmic patterns with a stack augmented recurrent network", by Armand Joulin and Tomas Mikolov.

stanford-shapenet-renderer

Scripts for batch rendering models using Blender. Tested with models from stanfords shapenet library.

starless

Starless is a CPU black hole raytracer in numpy suitable for both informative diagrams and decent wallpaper material.

style2paints

sketch + style = paints :art:

taichi

Open-Source Computer Graphics Library

ted-multilingual-parallel-corpus

TED parallel Corpora is growing collection of Bilingual parallel corpora, Multilingual parallel corpora and Monolingual corpora extracted from TED talks www.ted.com for 109 world languages.

tensor2tensor

A library for generalized sequence to sequence models

tensorf

Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields

theano-rnn

Demonstration of recurrent neural network implemented with Theano

threestudio

A unified framework for 3D content generation.

tiny-cuda-nn

Lightning fast & tiny C++/CUDA neural network framework

tmbp