af-74413592 Goto Github PK

pytorch-nce

The Noise Contrastive Estimation for softmax output written in Pytorch

pytorch-transformerxl-longtextclassify

pytorch-unet

Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation

pytorch-vae

A Collection of Variational Autoencoders (VAE) in PyTorch.

pytorch-vae-1

A Variational Autoencoder (VAE) implemented in PyTorch

pytorch-wgan

Pytorch implementation of DCGAN, WGAN-CP, WGAN-GP

pytorch_bert_multihead_ner

使用多头的**来进行命名实体识别

pytorch_retinaface

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

quick_sentence_transformers

ranger21

Ranger deep learning optimizer rewrite to use newest components

rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

react

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

read_bert_code

Bert源码阅读与讲解(Pytorch版本)-以BERT文本分类代码为例子

recommender-system-pytorch

基于 Pytorch 实现推荐系统相关的算法

recommendersystem

recon

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

reflection_summary

算法理论基础知识应知应会

reflexion

Reflexion: an autonomous agent with dynamic memory and self-reflection

regionclip

[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"

regnet

Not Totally Accurate [RegNet: Multimodal Sensor Registration Using Deep Neural Networks] PyTorch Implementation

reid-strong-baseline

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

reid_tutorial_slides

《深度学习与行人重识别》课程课件

repdistiller

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

rerope

Rectified Rotary Position Embeddings

retnet

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

rnn

roformer

Rotary Transformer

rsalgorithms

all kinds of recommendation algorithms implement.

rwkv-lm

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (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.