파이토치(PyTorch) 튜토리얼에 오신 것을 환영합니다¶
여러분의 생각을 들려주세요. (비공식) 한국어 PyTorch 튜토리얼 독자 설문에 참여 부탁드립니다.
PyTorch 기본 익히기
PyTorch로 전체 ML워크플로우를 구축하기 위한 단계별 학습 가이드입니다.
예제로 배우는 파이토치(PyTorch)
튜토리얼에 포함된 예제들로 PyTorch의 기본 개념을 이해합니다.
What is torch.nn really?
Use torch.nn to create and train a neural network.
TensorBoard로 모델, 데이터, 학습 시각화하기
TensorBoard로 데이터 및 모델 교육을 시각화하는 방법을 배웁니다.
TorchVision 객체 검출 미세조정(Finetuning) 튜토리얼
이미 훈련된 Mask R-CNN 모델을 미세조정합니다.
컴퓨터 비전을 위한 전이학습(TRANSFER LEARNING) 튜토리얼
전이학습으로 이미지 분류를 위한 합성곱 신경망을 학습합니다.
Optimizing Vision Transformer Model
Apply cutting-edge, attention-based transformer models to computer vision tasks.
적대적 예제 생성(Adversarial Example Generation)
가장 많이 사용되는 공격 방법 중 하나인 FGSM (Fast Gradient Sign Attack)을 이용해 MNIST 분류기를 속이는 방법을 배웁니다.
DCGAN Tutorial
Train a generative adversarial network (GAN) to generate new celebrities.
nn.Transformer 와 TorchText 로 시퀀스-투-시퀀스 모델링하기
nn.Transformer 모듈을 사용하여 어떻게 시퀀스-투-시퀀스(Seq-to-Seq) 모델을 학습하는지 배웁니다.
기초부터 시작하는 NLP: 문자-단위 RNN으로 이름 분류하기
torchtext를 사용하지 않고 기본적인 문자-단위 RNN을 사용하여 단어를 분류하는 모델을 기초부터 만들고 학습합니다. 총 3개로 이뤄진 튜토리얼 시리즈의 첫번째 편입니다.
기초부터 시작하는 NLP: 문자-단위 RNN으로 이름 생성하기
문자-단위 RNN을 사용하여 이름을 분류해봤으니, 이름을 생성하는 방법을 학습합니다. 총 3개로 이뤄진 튜토리얼 시리즈 중 두번째 편입니다.
기초부터 시작하는 NLP: 시퀀스-투-시퀀스 네트워크와 어텐션을 이용한 번역
“기초부터 시작하는 NLP”의 세번째이자 마지막 편으로, NLP 모델링 작업을 위한 데이터 전처리에 사용할 자체 클래스와 함수들을 작성해보겠습니다.
Text Classification with Torchtext
This is the third and final tutorial on doing “NLP From Scratch”, where we write our own classes and functions to preprocess the data to do our NLP modeling tasks.
TorchText로 언어 번역하기
영어와 독어가 포함된 잘 알려진 데이터셋을 torchtext를 사용하여 전처리한 뒤, 시퀀스-투-시퀀스(Seq-to-Seq) 모델을 사용하여 학습합니다.
강화 학습(DQN) 튜토리얼
PyTorch를 사용하여 OpenAI Gym의 CartPole-v0 태스크에서 DQN(Deep Q Learning) 에이전트를 학습하는 방법을 살펴봅니다.
Train a Mario-playing RL Agent
Use PyTorch to train a Double Q-learning agent to play Mario.
Flask를 사용하여 Python에서 PyTorch를 REST API로 배포하기
Flask를 사용하여 PyTorch 모델을 배포하고, 미리 학습된 DenseNet 121 모델을 예제로 활용하여 모델 추론(inference)을 위한 REST API를 만들어보겠습니다.
TorchScript 소개
C++과 같은 고성능 환경에서 실행할 수 있도록 (nn.Module의 하위 클래스인) PyTorch 모델의 중간 표현(intermediate representation)을 제공하는 TorchScript를 소개합니다.
C++에서 TorchScript 모델 로딩하기
PyTorch가 어떻게 기존의 Python 모델을 직렬화된 표현으로 변환하여 Python 의존성 없이 순수하게 C++에서 불러올 수 있는지 배웁니다.
(optional) Exporting a Model from PyTorch to ONNX and Running it using ONNX Runtime
Convert a model defined in PyTorch into the ONNX format and then run it with ONNX Runtime.
Building a Convolution/Batch Norm fuser in FX
Build a simple FX pass that fuses batch norm into convolution to improve performance during inference.
Building a Simple Performance Profiler with FX
Build a simple FX interpreter to record the runtime of op, module, and function calls and report statistics
(beta) Channels Last Memory Format in PyTorch
Get an overview of Channels Last memory format and understand how it is used to order NCHW tensors in memory preserving dimensions.
Using the PyTorch C++ Frontend
Walk through an end-to-end example of training a model with the C++ frontend by training a DCGAN – a kind of generative model – to generate images of MNIST digits.
Custom C++ and CUDA Extensions
Create a neural network layer with no parameters using numpy. Then use scipy to create a neural network layer that has learnable weights.
Extending TorchScript with Custom C++ Operators
Implement a custom TorchScript operator in C++, how to build it into a shared library, how to use it in Python to define TorchScript models and lastly how to load it into a C++ application for inference workloads.
Extending TorchScript with Custom C++ Classes
This is a continuation of the custom operator tutorial, and introduces the API we’ve built for binding C++ classes into TorchScript and Python simultaneously.
Dynamic Parallelism in TorchScript
This tutorial introduces the syntax for doing *dynamic inter-op parallelism* in TorchScript.
Autograd in C++ Frontend
The autograd package helps build flexible and dynamic nerural netorks. In this tutorial, exploreseveral examples of doing autograd in PyTorch C++ frontend
Registering a Dispatched Operator in C++
The dispatcher is an internal component of PyTorch which is responsible for figuring out what code should actually get run when you call a function like torch::add.
Extending Dispatcher For a New Backend in C++
Learn how to extend the dispatcher to add a new device living outside of the pytorch/pytorch repo and maintain it to keep in sync with native PyTorch devices.
Performance Profiling in PyTorch
Learn how to use the PyTorch Profiler to benchmark your module's performance.
Hyperparameter Tuning Tutorial
Learn how to use Ray Tune to find the best performing set of hyperparameters for your model.
Pruning Tutorial
Learn how to use torch.nn.utils.prune to sparsify your neural networks, and how to extend it to implement your own custom pruning technique.
(beta) Dynamic Quantization on an LSTM Word Language Model
Apply dynamic quantization, the easiest form of quantization, to a LSTM-based next word prediction model.
(beta) Dynamic Quantization on BERT
Apply the dynamic quantization on a BERT (Bidirectional Embedding Representations from Transformers) model.
(beta) Quantized Transfer Learning for Computer Vision Tutorial
Extends the Transfer Learning for Computer Vision Tutorial using a quantized model.
PyTorch Distributed Overview
Briefly go over all concepts and features in the distributed package. Use this document to find the distributed training technology that can best serve your application.
Single-Machine Model Parallel Best Practices
Learn how to implement model parallel, a distributed training technique which splits a single model onto different GPUs, rather than replicating the entire model on each GPU
Getting Started with Distributed Data Parallel
Learn the basics of when to use distributed data paralle versus data parallel and work through an example to set it up.
PyTorch로 분산 어플리케이션 개발하기
PyTorch의 분산 패키지를 설정하고, 서로 다른 통신 전략을 사용하고, 내부를 살펴봅니다.
Getting Started with Distributed RPC Framework
Learn how to build distributed training using the torch.distributed.rpc package.
Implementing a Parameter Server Using Distributed RPC Framework
Walk through a through a simple example of implementing a parameter server using PyTorch’s Distributed RPC framework.
Distributed Pipeline Parallelism Using RPC
Demonstrate how to implement distributed pipeline parallelism using RPC
Implementing Batch RPC Processing Using Asynchronous Executions
Learn how to use rpc.functions.async_execution to implement batch RPC
Combining Distributed DataParallel with Distributed RPC Framework
Walk through a through a simple example of how to combine distributed data parallelism with distributed model parallelism.
Training Transformer models using Pipeline Parallelism
Walk through a through a simple example of how to train a transformer model using pipeline parallelism.
Training Transformer models using Distributed Data Parallel and Pipeline Parallelism
Walk through a through a simple example of how to train a transformer model using Distributed Data Parallel and Pipeline Parallelism
Image Segmentation DeepLabV3 on iOS
A comprehensive step-by-step tutorial on how to prepare and run the PyTorch DeepLabV3 image segmentation model on iOS.
Image Segmentation DeepLabV3 on Android
A comprehensive step-by-step tutorial on how to prepare and run the PyTorch DeepLabV3 image segmentation model on Android.
