annotated_deep_learning_paper_implementations

2025-12-10 0 407

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.

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

Paper Implementations

Transformers

  • Multi-headed attention
  • Transformer building blocks
  • Transformer XL
    • Relative multi-headed attention
  • Rotary Positional Embeddings
  • Attention with Linear Biases (ALiBi)
  • RETRO
  • Compressive Transformer
  • GPT Architecture
  • GLU Variants
  • kNN-LM: Generalization through Memorization
  • Feedback Transformer
  • Switch Transformer
  • Fast Weights Transformer
  • FNet
  • Attention Free Transformer
  • Masked Language Model
  • MLP-Mixer: An all-MLP Architecture for Vision
  • Pay Attention to MLPs (gMLP)
  • Vision Transformer (ViT)
  • Primer EZ
  • Hourglass

Low-Rank Adaptation (LoRA)

Eleuther GPT-NeoX

  • Generate on a 48GB GPU
  • Finetune on two 48GB GPUs
  • LLM.int8()

Diffusion models

  • Denoising Diffusion Probabilistic Models (DDPM)
  • Denoising Diffusion Implicit Models (DDIM)
  • Latent Diffusion Models
  • Stable Diffusion

Generative Adversarial Networks

  • Original GAN
  • GAN with deep convolutional network
  • Cycle GAN
  • Wasserstein GAN
  • Wasserstein GAN with Gradient Penalty
  • StyleGAN 2

Recurrent Highway Networks

LSTM

HyperNetworks – HyperLSTM

ResNet

ConvMixer

Capsule Networks

U-Net

Sketch RNN

Graph Neural Networks

  • Graph Attention Networks (GAT)
  • Graph Attention Networks v2 (GATv2)

Counterfactual Regret Minimization (CFR)

Solving games with incomplete information such as poker with CFR.

  • Kuhn Poker

Reinforcement Learning

  • Proximal Policy Optimization with
    Generalized Advantage Estimation
  • Deep Q Networks with
    with Dueling Network,
    Prioritized Replay
    and Double Q Network.

Optimizers

  • Adam
  • AMSGrad
  • Adam Optimizer with warmup
  • Noam Optimizer
  • Rectified Adam Optimizer
  • AdaBelief Optimizer
  • Sophia-G Optimizer

Normalization Layers

  • Batch Normalization
  • Layer Normalization
  • Instance Normalization
  • Group Normalization
  • Weight Standardization
  • Batch-Channel Normalization
  • DeepNorm

Distillation

Adaptive Computation

  • PonderNet

Uncertainty

  • Evidential Deep Learning to Quantify Classification Uncertainty

Activations

  • Fuzzy Tiling Activations

Langauge Model Sampling Techniques

  • Greedy Sampling
  • Temperature Sampling
  • Top-k Sampling
  • Nucleus Sampling

Scalable Training/Inference

  • Zero3 memory optimizations

Installation

pip install labml-nn

下载源码

通过命令行克隆项目:

git clone https://github.com/labmlai/annotated_deep_learning_paper_implementations.git

收藏 (0) 打赏

感谢您的支持,我会继续努力的!

打开微信/支付宝扫一扫,即可进行扫码打赏哦,分享从这里开始,精彩与您同在
点赞 (0)

申明:本文由第三方发布,内容仅代表作者观点,与本网站无关。对本文以及其中全部或者部分内容的真实性、完整性、及时性本站不作任何保证或承诺,请读者仅作参考,并请自行核实相关内容。本网发布或转载文章出于传递更多信息之目的,并不意味着赞同其观点或证实其描述,也不代表本网对其真实性负责。

左子网 编程相关 annotated_deep_learning_paper_implementations https://www.zuozi.net/33098.html

keras
上一篇: keras
web develop
下一篇: web develop
常见问题
  • 1、自动:拍下后,点击(下载)链接即可下载;2、手动:拍下后,联系卖家发放即可或者联系官方找开发者发货。
查看详情
  • 1、源码默认交易周期:手动发货商品为1-3天,并且用户付款金额将会进入平台担保直到交易完成或者3-7天即可发放,如遇纠纷无限期延长收款金额直至纠纷解决或者退款!;
查看详情
  • 1、描述:源码描述(含标题)与实际源码不一致的(例:货不对板); 2、演示:有演示站时,与实际源码小于95%一致的(但描述中有”不保证完全一样、有变化的可能性”类似显著声明的除外); 3、发货:不发货可无理由退款; 4、安装:免费提供安装服务的源码但卖家不履行的; 5、收费:价格虚标,额外收取其他费用的(但描述中有显著声明或双方交易前有商定的除外); 6、其他:如质量方面的硬性常规问题BUG等。 注:经核实符合上述任一,均支持退款,但卖家予以积极解决问题则除外。
查看详情
  • 1、左子会对双方交易的过程及交易商品的快照进行永久存档,以确保交易的真实、有效、安全! 2、左子无法对如“永久包更新”、“永久技术支持”等类似交易之后的商家承诺做担保,请买家自行鉴别; 3、在源码同时有网站演示与图片演示,且站演与图演不一致时,默认按图演作为纠纷评判依据(特别声明或有商定除外); 4、在没有”无任何正当退款依据”的前提下,商品写有”一旦售出,概不支持退款”等类似的声明,视为无效声明; 5、在未拍下前,双方在QQ上所商定的交易内容,亦可成为纠纷评判依据(商定与描述冲突时,商定为准); 6、因聊天记录可作为纠纷评判依据,故双方联系时,只与对方在左子上所留的QQ、手机号沟通,以防对方不承认自我承诺。 7、虽然交易产生纠纷的几率很小,但一定要保留如聊天记录、手机短信等这样的重要信息,以防产生纠纷时便于左子介入快速处理。
查看详情

相关文章

猜你喜欢
发表评论
暂无评论
官方客服团队

为您解决烦忧 - 24小时在线 专业服务