labml.ai 深度学习论文实现

60 篇深度学习论文的实现/教程,并附有旁注;包括 transformers(Original, xl, switch, feedback, vit, ...),优化器(adam, adabelief, ...),gans(cyclegan, stylegan2, ...),🎮强化学习(ppo, dqn),capnet, 蒸馏, ...。「🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠」

Twitter
Sponsor

labml.ai Deep Learning Paper Implementations

This is a collection of simple PyTorch implementations of
neural networks and related algorithms.
These implementations are documented with explanations,

The website
renders these as side-by-side formatted notes.
We believe these would help you understand these algorithms better.

Screenshot

We are actively maintaining this repo and adding new
implementations almost weekly.
Twitter for updates.

Paper Implementations

Transformers

Low-Rank Adaptation (LoRA)

Eleuther GPT-NeoX

Diffusion models

Generative Adversarial Networks

Recurrent Highway Networks

LSTM

HyperNetworks - HyperLSTM

ResNet

ConvMixer

Capsule Networks

U-Net

Sketch RNN

✨ Graph Neural Networks

Counterfactual Regret Minimization (CFR)

Solving games with incomplete information such as poker with CFR.

Reinforcement Learning

Optimizers

Normalization Layers

Distillation

Adaptive Computation

Uncertainty

Activations

Langauge Model Sampling Techniques

Scalable Training/Inference

Installation

pip install labml-nn

主要指標

概覽
名稱與所有者labmlai/annotated_deep_learning_paper_implementations
主編程語言Python
編程語言Python (語言數: 3)
平台
許可證MIT License
所有者活动
創建於2020-08-25 02:29:34
推送於2024-08-24 09:18:59
最后一次提交2024-08-24 14:48:59
發布數0
用户参与
星數60.9k
關注者數476
派生數6.1k
提交數829
已啟用問題?
問題數137
打開的問題數31
拉請求數100
打開的拉請求數6
關閉的拉請求數19
项目设置
已啟用Wiki?
已存檔?
是復刻?
已鎖定?
是鏡像?
是私有?