{ "

Annotated Research Paper Implementations: Transformers, StyleGAN, Stable Diffusion, DDPM/DDIM, LayerNorm, Nucleus Sampling and more

\n": "

labml.ai \u5e26\u6ce8\u91ca\u7684 PyTorch \u7248\u8bba\u6587\u5b9e\u73b0

\n", "

Paper Implementations

\n": "

\u8bba\u6587\u5b9e\u73b0

\n", "

Translations

\n": "

\u7ffb\u8bd1

\n", "

English (original)

\n": "

\u82f1\u8bed\uff08\u539f\u7248\uff09

\n", "

Japanese (translated)

\n": "

\u65e5\u8bed\uff08\u7ffb\u8bd1\uff09

\n", "

Chinese (translated)

\n": "

\u4e2d\u6587\uff08\u7ffb\u8bd1\uff09

\n", "

Installation

\n": "

\u5b89\u88c5

\n", "

\u2728 Activations

\n": "

\u2728 \u6fc0\u6d3b\u51fd\u6570

\n", "

\u2728 Adaptive Computation

\n": "

\u2728 \u81ea\u9002\u5e94\u8ba1\u7b97

\n", "

\u2728 Capsule Networks

\n": "

\u2728 \u80f6\u56ca\u7f51\u7edc

\n", "

\u2728 Counterfactual Regret Minimization (CFR)

\n": "

\u2728 \u865a\u62df\u9057\u61be\u6700\u5c0f\u5316\uff08CFR\uff09

\n", "

\u2728 ConvMixer

\n": "

\u2728 ConvMixer

\n", "

\u2728 Diffusion models

\n": "

\u2728 \u6269\u6563\u6a21\u578b

\n", "

\u2728 Distillation

\n": "

\u2728 \u84b8\u998f

\n", "

\u2728 Generative Adversarial Networks

\n": "

\u2728 \u751f\u6210\u5bf9\u6297\u7f51\u7edc

\n", "

\u2728 HyperNetworks - HyperLSTM

\n": "

\u2728 \u8d85\u7f51\u7edc-HyperLSTM

\n", "

\u2728 Low-Rank Adaptation (LoRA)

\n": "

\u2728 Low-Rank Adaptation (LoRA)

\n", "

\u2728 LSTM

\n": "

\u2728 LSTM

\n", "

\u2728 Eleuther GPT-NeoX

\n": "

\u2728 Eleuther GPT-neox

\n", "

\u2728 Normalization Layers

\n": "

\u2728 \u5f52\u4e00\u5316\u5c42

\n", "

\u2728 Optimizers

\n": "

\u2728 \u4f18\u5316\u5668

\n", "

\u2728 Recurrent Highway Networks

\n": "

\u2728 \u5faa\u73af\u9ad8\u901f\u8def\u7f51\u7edc

\n", "

\u2728 ResNet

\n": "

\u2728 ResNet

\n", "

\u2728 Reinforcement Learning

\n": "

\u2728 \u5f3a\u5316\u5b66\u4e60

\n", "

\u2728 Language Model Sampling Techniques

\n": "

\u2728 \u8bed\u8a00\u6a21\u578b\u91c7\u6837\u6280\u672f

\n", "

\u2728 Scalable Training/Inference

\n": "

\u2728 \u53ef\u6269\u5c55\u8bad\u7ec3/\u63a8\u7406

\n", "

\u2728 Sketch RNN

\n": "

\u2728 Sketch RNN

\n", "

\u2728 Transformers

\n": "

\u2728 Transformers

\n", "

\u2728 Uncertainty

\n": "

\u2728 \u4e0d\u786e\u5b9a\u6027

\n", "

\u2728 U-Net

\n": "

\u2728 U-Net

\n", "

\u2728 Graph Neural Networks

\n": "

\u2728 \u56fe\u795e\u7ecf\u7f51\u7edc

\n", "

_^_0_^_

\n": "

_^_0_^_

\n", "

Solving games with incomplete information such as poker with CFR.

\n": "

\u4f7f\u7528 CFR \u89e3\u51b3\u8bf8\u5982\u6251\u514b\u7b49\u4e0d\u5b8c\u5168\u4fe1\u606f\u6e38\u620f

\n", "

This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations, and the website renders these as side-by-side formatted notes. We believe these would help you understand these algorithms better.

\n": "

\u8fd9\u662f\u4e00\u4e2a\u7528 PyTorch \u5b9e\u73b0\u5404\u79cd\u795e\u7ecf\u7f51\u7edc\u548c\u76f8\u5173\u7b97\u6cd5\u7684\u96c6\u5408\u3002\u6bcf\u4e2a\u7b97\u6cd5\u7684\u4ee3\u7801\u5b9e\u73b0\u90fd\u6709\u8be6\u7ec6\u7684\u89e3\u91ca\u8bf4\u660e\uff0c\u4e14\u5728\u7f51\u7ad9\u4e0a\u4e0e\u4ee3\u7801\u9010\u884c\u5bf9\u5e94\u3002\u6211\u4eec\u76f8\u4fe1\uff0c\u8fd9\u4e9b\u5185\u5bb9\u5c06\u5e2e\u52a9\u60a8\u66f4\u597d\u5730\u7406\u89e3\u8fd9\u4e9b\u7b97\u6cd5\u3002

\n", "

We are actively maintaining this repo and adding new implementations. _^_0_^_ for updates.

\n": "

\u6211\u4eec\u6b63\u5728\u79ef\u6781\u7ef4\u62a4\u8fd9\u4e2a\u4ed3\u5e93\u5e76\u6dfb\u52a0\u65b0\u7684\u4ee3\u7801\u5b9e\u73b0\u3002_^_0_^_\u4ee5\u83b7\u53d6\u66f4\u65b0\u3002

\n", "_^_0_^_": "_^_0_^_", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "\n": "\n", "Annotated Research Paper Implementations: Transformers, StyleGAN, Stable Diffusion, DDPM/DDIM, LayerNorm, Nucleus Sampling and more": "labml.ai \u5e26\u6ce8\u91ca\u7684 PyTorch \u7248\u8bba\u6587\u5b9e\u73b0" }