From 73467dac83e037c7878631e73cf3a1e4a75f5190 Mon Sep 17 00:00:00 2001 From: wehub-resource-sync Date: Mon, 13 Jul 2026 10:39:06 +0000 Subject: [PATCH] docs: make Chinese README the default --- README.md | 484 +++++++++++++++++++++++++++--------------------------- 1 file changed, 245 insertions(+), 239 deletions(-) diff --git a/README.md b/README.md index a886139..0fc2fd1 100644 --- a/README.md +++ b/README.md @@ -1,293 +1,299 @@ -# Learn PyTorch for Deep Learning + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/mrdbourke/pytorch-deep-learning) · [上游 README](https://github.com/mrdbourke/pytorch-deep-learning/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 -Welcome to the [Zero to Mastery Learn PyTorch for Deep Learning course](https://dbourke.link/ZTMPyTorch), the second best place to learn PyTorch on the internet (the first being the [PyTorch documentation](https://pytorch.org/docs/stable/index.html)). +# 学习 PyTorch 深度学习 -* **Update April 2023:** New [tutorial for PyTorch 2.0](https://www.learnpytorch.io/pytorch_2_intro/) is live! And because PyTorch 2.0 is an additive (new features) and backward-compatible release, all previous course materials will *still* work with PyTorch 2.0. +欢迎来到 [Zero to Mastery Learn PyTorch for Deep Learning 课程](https://dbourke.link/ZTMPyTorch),——互联网上学习 PyTorch 的第二好去处（第一好是 [PyTorch 文档](https://pytorch.org/docs/stable/index.html)). + +* **2023 年 4 月更新：** 全新的 [PyTorch 2.0 教程](https://www.learnpytorch.io/pytorch_2_intro/) 已上线！由于 PyTorch 2.0 是增量式（新功能）且向后兼容的发布，所有先前的课程材料在 PyTorch 2.0 下*仍然*可用。
- pytorch deep learning by zero to mastery cover photo with different sections of the course + Zero to Mastery PyTorch 深度学习课程封面，展示课程的不同章节
-## Contents of this page +## 本页目录 -* [Course materials/outline](https://github.com/mrdbourke/pytorch-deep-learning#course-materialsoutline) -* [About this course](https://github.com/mrdbourke/pytorch-deep-learning#about-this-course) -* [Status](https://github.com/mrdbourke/pytorch-deep-learning#status) (the progress of the course creation) -* [Log](https://github.com/mrdbourke/pytorch-deep-learning#log) (a log of the course material creation process) +* [课程材料/大纲](https://github.com/mrdbourke/pytorch-deep-learning#course-materialsoutline) +* [关于本课程](https://github.com/mrdbourke/pytorch-deep-learning#about-this-course) +* [状态](https://github.com/mrdbourke/pytorch-deep-learning#status)（课程制作进度） +* [日志](https://github.com/mrdbourke/pytorch-deep-learning#log)（课程材料制作过程的记录） -## Course materials/outline +## 课程材料/大纲 -* 📖 **Online book version:** All of course materials are available in a readable online book at [learnpytorch.io](https://learnpytorch.io). -* 🎥 **First five sections on YouTube:** Learn PyTorch in a day by watching the [first 25 hours of material](https://youtu.be/Z_ikDlimN6A). -* 🔬 **Course focus:** code, code, code, experiment, experiment, experiment. -* 🏃‍♂️ **Teaching style:** [https://sive.rs/kimo](https://sive.rs/kimo). -* 🤔 **Ask a question:** See the [GitHub Discussions page](https://github.com/mrdbourke/pytorch-deep-learning/discussions) for existing questions/ask your own. +* 📖 **在线书籍版本：** 所有课程材料均可在 [learnpytorch.io](https://learnpytorch.io). 在线阅读。 +* 🎥 **YouTube 上前五章：** 观看 [前 25 小时的内容](https://youtu.be/Z_ikDlimN6A).，一天学会 PyTorch。 +* 🔬 **课程重点：** 代码、代码、代码，实验、实验、实验。 +* 🏃‍♂️ **教学风格：** [https://sive.rs/kimo](https://sive.rs/kimo). +* 🤔 **提问：** 请前往 [GitHub Discussions 页面](https://github.com/mrdbourke/pytorch-deep-learning/discussions) 查看已有问题或提出自己的问题。 -| **Section** | **What does it cover?** | **Exercises & Extra-curriculum** | **Slides** | +| **章节** | **涵盖内容** | **练习与课外拓展** | **幻灯片** | | ----- | ----- | ----- | ----- | -| [00 - PyTorch Fundamentals](https://www.learnpytorch.io/00_pytorch_fundamentals/) | Many fundamental PyTorch operations used for deep learning and neural networks. | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/00_pytorch_fundamentals/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/00_pytorch_and_deep_learning_fundamentals.pdf) | -| [01 - PyTorch Workflow](https://www.learnpytorch.io/01_pytorch_workflow/) | Provides an outline for approaching deep learning problems and building neural networks with PyTorch. | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/01_pytorch_workflow/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/01_pytorch_workflow.pdf) | -| [02 - PyTorch Neural Network Classification](https://www.learnpytorch.io/02_pytorch_classification/) | Uses the PyTorch workflow from 01 to go through a neural network classification problem. | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/02_pytorch_classification/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/02_pytorch_classification.pdf) | -| [03 - PyTorch Computer Vision](https://www.learnpytorch.io/03_pytorch_computer_vision/) | Let's see how PyTorch can be used for computer vision problems using the same workflow from 01 & 02. | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/03_pytorch_computer_vision/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/03_pytorch_computer_vision.pdf) | -| [04 - PyTorch Custom Datasets](https://www.learnpytorch.io/04_pytorch_custom_datasets/) | How do you load a custom dataset into PyTorch? Also we'll be laying the foundations in this notebook for our modular code (covered in 05). | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/04_pytorch_custom_datasets/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/04_pytorch_custom_datasets.pdf) | -| [05 - PyTorch Going Modular](https://www.learnpytorch.io/05_pytorch_going_modular/) | PyTorch is designed to be modular, let's turn what we've created into a series of Python scripts (this is how you'll often find PyTorch code in the wild). | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/05_pytorch_going_modular/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/05_pytorch_going_modular.pdf) | -| [06 - PyTorch Transfer Learning](https://www.learnpytorch.io/06_pytorch_transfer_learning/) | Let's take a well performing pre-trained model and adjust it to one of our own problems. | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/06_pytorch_transfer_learning/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/06_pytorch_transfer_learning.pdf) | -| [07 - Milestone Project 1: PyTorch Experiment Tracking](https://www.learnpytorch.io/07_pytorch_experiment_tracking/) | We've built a bunch of models... wouldn't it be good to track how they're all going? | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/07_pytorch_experiment_tracking/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/07_pytorch_experiment_tracking.pdf) | -| [08 - Milestone Project 2: PyTorch Paper Replicating](https://www.learnpytorch.io/08_pytorch_paper_replicating/) | PyTorch is the most popular deep learning framework for machine learning research, let's see why by replicating a machine learning paper. | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/08_pytorch_paper_replicating/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/08_pytorch_paper_replicating.pdf) | -| [09 - Milestone Project 3: Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/) | So we've built a working PyTorch model... how do we get it in the hands of others? Hint: deploy it to the internet. | [Go to exercises & extra-curriculum](https://www.learnpytorch.io/09_pytorch_model_deployment/#exercises) | [Go to slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/09_pytorch_model_deployment.pdf) | -| [PyTorch Extra Resources](https://www.learnpytorch.io/pytorch_extra_resources/) | This course covers a large amount of PyTorch and deep learning but the field of machine learning is vast, inside here you'll find recommended books and resources for: PyTorch and deep learning, ML engineering, NLP (natural language processing), time series data, where to find datasets and more. | - | - | -| [PyTorch Cheatsheet](https://www.learnpytorch.io/pytorch_cheatsheet/) | A very quick overview of some of the main features of PyTorch plus links to various resources where more can be found in the course and in the PyTorch documentation. | - | - | -| [A Quick PyTorch 2.0 Tutorial](https://www.learnpytorch.io/pytorch_2_intro/) | A fasssssst introduction to PyTorch 2.0, what's new and how to get started along with resources to learn more. | - | - | +| [00 - PyTorch 基础](https://www.learnpytorch.io/00_pytorch_fundamentals/) | 深度学习和神经网络中常用的诸多基础 PyTorch 操作。 | [前往练习与课外拓展](https://www.learnpytorch.io/00_pytorch_fundamentals/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/00_pytorch_and_deep_learning_fundamentals.pdf) | +| [01 - PyTorch 工作流](https://www.learnpytorch.io/01_pytorch_workflow/) | 提供用 PyTorch 解决深度学习问题并构建神经网络的思路大纲。 | [前往练习与课外拓展](https://www.learnpytorch.io/01_pytorch_workflow/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/01_pytorch_workflow.pdf) | +| [02 - PyTorch 神经网络分类](https://www.learnpytorch.io/02_pytorch_classification/) | 运用第 01 章的 PyTorch 工作流，完成一个神经网络分类问题。 | [前往练习与课外拓展](https://www.learnpytorch.io/02_pytorch_classification/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/02_pytorch_classification.pdf) | +| [03 - PyTorch 计算机视觉](https://www.learnpytorch.io/03_pytorch_computer_vision/) | 看看如何沿用第 01、02 章的工作流，用 PyTorch 解决计算机视觉问题。 | [前往练习与课外拓展](https://www.learnpytorch.io/03_pytorch_computer_vision/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/03_pytorch_computer_vision.pdf) | +| [04 - PyTorch 自定义数据集](https://www.learnpytorch.io/04_pytorch_custom_datasets/) | 如何将自定义数据集加载到 PyTorch 中？本 notebook 还会为模块化代码（第 05 章介绍）打下基础。 | [前往练习与课外拓展](https://www.learnpytorch.io/04_pytorch_custom_datasets/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/04_pytorch_custom_datasets.pdf) | +| [05 - PyTorch 模块化](https://www.learnpytorch.io/05_pytorch_going_modular/) | PyTorch 的设计注重模块化；让我们把已创建的内容整理成一系列 Python 脚本（这也是你在实际项目中常见的 PyTorch 代码组织方式）。 | [前往练习与课外拓展](https://www.learnpytorch.io/05_pytorch_going_modular/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/05_pytorch_going_modular.pdf) | +| [06 - PyTorch 迁移学习](https://www.learnpytorch.io/06_pytorch_transfer_learning/) | 选取一个表现优异的预训练模型，并针对我们自己的问题进行调整。 | [前往练习与课外拓展](https://www.learnpytorch.io/06_pytorch_transfer_learning/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/06_pytorch_transfer_learning.pdf) | +| [07 - 里程碑项目 1：PyTorch 实验追踪](https://www.learnpytorch.io/07_pytorch_experiment_tracking/) | 我们已经构建了不少模型……要是能追踪它们各自的进展该多好？ | [前往练习与课外拓展](https://www.learnpytorch.io/07_pytorch_experiment_tracking/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/07_pytorch_experiment_tracking.pdf) | +| [08 - 里程碑项目 2：PyTorch 论文复现](https://www.learnpytorch.io/08_pytorch_paper_replicating/) | PyTorch 是机器学习研究领域最流行的深度学习框架；让我们通过复现一篇机器学习论文来一探究竟。 | [前往练习与课外拓展](https://www.learnpytorch.io/08_pytorch_paper_replicating/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/08_pytorch_paper_replicating.pdf) | +| [09 - 里程碑项目 3：模型部署](https://www.learnpytorch.io/09_pytorch_model_deployment/) | 我们已经有了一个可运行的 PyTorch 模型……如何把它交到他人手中？提示：部署到互联网上。 | [前往练习与课外拓展](https://www.learnpytorch.io/09_pytorch_model_deployment/#exercises) | [前往幻灯片](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/09_pytorch_model_deployment.pdf) | +| [PyTorch 额外资源](https://www.learnpytorch.io/pytorch_extra_resources/) | 本课程涵盖大量 PyTorch 与深度学习内容，但机器学习领域十分广阔；此处收录了推荐书籍与资源，涵盖：PyTorch 与深度学习、ML 工程、NLP（自然语言处理）、时间序列数据、数据集获取途径等。 | - | - | +| [PyTorch 速查表](https://www.learnpytorch.io/pytorch_cheatsheet/) | 快速概览 PyTorch 的部分主要特性，并提供课程内及 PyTorch 文档中更多资源的链接。 | - | - | +| [PyTorch 2.0 快速教程](https://www.learnpytorch.io/pytorch_2_intro/) | 对 PyTorch 2.0 的超快快快快快入门介绍：有哪些新内容、如何开始，以及进一步学习的资源。 | - | - | -## Status +## 状态 -All materials completed and videos published on Zero to Mastery! +所有材料均已完成，视频已在 Zero to Mastery 发布！ -See the project page for work-in-progress board - https://github.com/users/mrdbourke/projects/1 +请参阅项目页面上的进行中看板 - https://github.com/users/mrdbourke/projects/1 -* **Total video count:** 321 -* **Done skeleton code for:** 00, 01, 02, 03, 04, 05, 06, 07, 08, 09 -* **Done annotations (text) for:** 00, 01, 02, 03, 04, 05, 06, 07, 08, 09 -* **Done images for:** 00, 01, 02, 03, 04, 05, 06, 07, 08, 09 -* **Done keynotes for:** 00, 01, 02, 03, 04, 05, 06, 07, 08, 09 -* **Done exercises and solutions for:** 00, 01, 02, 03, 04, 05, 06, 07, 08, 09 +* **视频总数：** 321 +* **已完成骨架代码：** 00、01、02、03、04、05、06、07、08、09 +* **已完成注释（文本）：** 00、01、02、03、04、05、06、07、08、09 +* **已完成配图：** 00、01、02、03、04、05、06、07、08、09 +* **已完成主题演讲：** 00、01、02、03、04、05、06、07、08、09 +* **已完成练习与解答：** 00、01、02、03、04、05、06、07、08、09 -See the [log](https://github.com/mrdbourke/pytorch-deep-learning#log) for almost daily updates. +请参阅[日志](https://github.com/mrdbourke/pytorch-deep-learning#log) 获取几乎每日更新的内容。 -## About this course +## 关于本课程 -### Who is this course for? +### 本课程适合谁？ -**You:** Are a beginner in the field of machine learning or deep learning and would like to learn PyTorch. +**你：** 是机器学习或深度学习领域的初学者，希望学习 PyTorch。 -**This course:** Teaches you PyTorch and many machine learning concepts in a hands-on, code-first way. +**本课程：** 以动手实践、代码优先的方式，教你 PyTorch 以及许多机器学习（machine learning）概念。 -If you already have 1-year+ experience in machine learning, this course may help but it is specifically designed to be beginner-friendly. +如果你已有 1 年以上机器学习经验，本课程仍可能有帮助，但它专为初学者友好而设计。 -### What are the prerequisites? +### 先修要求是什么？ -1. 3-6 months coding Python. -2. At least one beginner machine learning course (however this might be able to be skipped, resources are linked for many different topics). -3. Experience using Jupyter Notebooks or Google Colab (though you can pick this up as we go along). -4. A willingness to learn (most important). +1. 3–6 个月 Python 编程经验。 +2. 至少一门机器学习入门课程（不过这一步或许可以跳过，文中为许多不同主题提供了资源链接）。 +3. 有使用 Jupyter Notebooks 或 Google Colab 的经验（当然你也可以边学边掌握）。 +4. 愿意学习（最重要）。 -For 1 & 2, I'd recommend the [Zero to Mastery Data Science and Machine Learning Bootcamp](https://dbourke.link/ZTMMLcourse), it'll teach you the fundamentals of machine learning and Python (I'm biased though, I also teach that course). +对于第 1 和第 2 点，我推荐 [Zero to Mastery Data Science and Machine Learning Bootcamp](https://dbourke.link/ZTMMLcourse), 它会教你机器学习和 Python 的基础知识（不过我有私心，我也教那门课）。 -### How is the course taught? +### 课程如何讲授？ -All of the course materials are available for free in an online book at [learnpytorch.io](https://learnpytorch.io). If you like to read, I'd recommend going through the resources there. +所有课程材料均可免费在线阅读，见 [learnpytorch.io](https://learnpytorch.io). 如果你喜欢阅读，我建议你通读那里的资源。 -If you prefer to learn via video, the course is also taught in apprenticeship-style format, meaning I write PyTorch code, you write PyTorch code. +如果你更喜欢通过视频学习，本课程也采用学徒式（apprenticeship-style）授课：我写 PyTorch 代码，你也写 PyTorch 代码。 -There's a reason the course motto's include *if in doubt, run the code* and *experiment, experiment, experiment!*. +课程座右铭里有两句很有道理：*如有疑问，就运行代码*（if in doubt, run the code），以及 *实验、实验、再实验！*（experiment, experiment, experiment!）。 -My whole goal is to help you to do one thing: learn machine learning by writing PyTorch code. +我的全部目标就是帮你做好一件事：通过编写 PyTorch 代码来学习机器学习。 -The code is all written via [Google Colab Notebooks](https://colab.research.google.com) (you could also use Jupyter Notebooks), an incredible free resource to experiment with machine learning. +所有代码都通过 [Google Colab Notebooks](https://colab.research.google.com) 编写（你也可以使用 Jupyter Notebooks），这是一个用于实验机器学习的绝佳免费资源。 -### What will I get if I finish the course? +### 完成课程后我能得到什么？ -There's certificates and all that jazz if you go through the videos. +如果你跟着视频学习，会有证书之类的东西。 -But certificates are meh. +但证书也就那样。 -You can consider this course a machine learning momentum builder. +你可以把本课程看作一个机器学习动量（momentum）构建器。 -By the end, you'll have written hundreds of lines of PyTorch code. +到课程结束时，你将编写数百行 PyTorch 代码。 -And will have been exposed to many of the most important concepts in machine learning. +并接触到机器学习中许多最重要的概念。 -So when you go to build your own machine learning projects or inspect a public machine learning project made with PyTorch, it'll feel familiar and if it doesn't, at least you'll know where to look. +因此，当你去构建自己的机器学习项目，或查看用 PyTorch 制作的公开机器学习项目时，你会觉得熟悉；即便不熟悉，至少你也知道该去哪里查找。 -### What will I build in the course? +### 课程里我会构建什么？ -We start with the barebone fundamentals of PyTorch and machine learning, so even if you're new to machine learning you'll be caught up to speed. +我们从 PyTorch 和机器学习最基础的内容开始，因此即使你刚接触机器学习，也能快速跟上进度。 -Then we’ll explore more advanced areas including PyTorch neural network classification, PyTorch workflows, computer vision, custom datasets, experiment tracking, model deployment, and my personal favourite: transfer learning, a powerful technique for taking what one machine learning model has learned on another problem and applying it to your own! +然后我们会探索更高级的领域，包括 PyTorch 神经网络分类、PyTorch 工作流、计算机视觉（computer vision）、自定义数据集、实验跟踪、模型部署，以及我个人最喜欢的：迁移学习（transfer learning）——一种强大技术，可把某个机器学习模型在另一问题上所学到的知识，应用到你自己的问题上！ -Along the way, you’ll build three milestone projects surrounding an overarching project called FoodVision, a neural network computer vision model to classify images of food. +在此过程中，你将围绕一个名为 FoodVision 的总项目完成三个里程碑项目：FoodVision 是一个用于对食物图像进行分类的神经网络计算机视觉模型。 -These milestone projects will help you practice using PyTorch to cover important machine learning concepts and create a portfolio you can show employers and say "here's what I've done". +这些里程碑项目将帮助你练习使用 PyTorch 覆盖重要的机器学习概念，并打造一份可以向雇主展示的作品集，说“这就是我做过的东西”。 -### How do I get started? +### 如何开始？ -You can read the materials on any device but this course is best viewed and coded along within a desktop browser. +你可以在任何设备上阅读材料，但本课程最好在桌面浏览器中观看并跟着编码。 -The course uses a free tool called Google Colab. If you've got no experience with it, I'd go through the free [Introduction to Google Colab tutorial](https://colab.research.google.com/notebooks/basic_features_overview.ipynb) and then come back here. +课程使用名为 Google Colab 的免费工具。如果你完全没有使用经验，建议先学习免费的 [Introduction to Google Colab tutorial](https://colab.research.google.com/notebooks/basic_features_overview.ipynb) 然后再回到这里。 -To start: +开始步骤： -1. Click on one of the notebook or section links above like "[00. PyTorch Fundamentals](https://www.learnpytorch.io/00_pytorch_fundamentals/)". -2. Click the "Open in Colab" button up the top. -3. Press SHIFT+Enter a few times and see what happens. +1. 点击上方某个 notebook 或章节链接，例如“[00. PyTorch Fundamentals](https://www.learnpytorch.io/00_pytorch_fundamentals/)”。 +2. 点击顶部的“Open in Colab”按钮。 +3. 按几次 SHIFT+Enter，看看会发生什么。 -### My question isn't answered +### 我的问题没有得到解答 -Please leave a [discussion](https://github.com/mrdbourke/pytorch-deep-learning/discussions) or send me an email directly: daniel (at) mrdbourke (dot) com. +请留下一条 [discussion](https://github.com/mrdbourke/pytorch-deep-learning/discussions) 或直接给我发邮件：daniel (at) mrdbourke (dot) com。 -## Log +## 日志 -Almost daily updates of what's happening. +几乎每天都会更新进展。 -* 15 May 2023 - PyTorch 2.0 tutorial finished + videos added to ZTM/Udemy, see code: https://www.learnpytorch.io/pytorch_2_intro/ -* 13 Apr 2023 - update PyTorch 2.0 notebook -* 30 Mar 2023 - update PyTorch 2.0 notebook with more info/clean code -* 23 Mar 2023 - upgrade PyTorch 2.0 tutorial with annotations and images -* 13 Mar 2023 - add starter code for PyTorch 2.0 tutorial -* 18 Nov 2022 - add a reference for 3 most common errors in PyTorch + links to course sections for more: https://www.learnpytorch.io/pytorch_most_common_errors/ -* 9 Nov 2022 - add PyTorch cheatsheet for a very quick overview of the main features of PyTorch + links to course sections: https://www.learnpytorch.io/pytorch_cheatsheet/ -* 9 Nov 2022 - full course materials (300+ videos) are now live on Udemy! You can sign up here: https://www.udemy.com/course/pytorch-for-deep-learning/?couponCode=ZTMGOODIES7 (launch deal code valid for 3-4 days from this line) -* 4 Nov 2022 - add a notebook for PyTorch Cheatsheet in `extras/` (a simple overview of many of the most important functionality of PyTorch) -* 2 Oct 2022 - all videos for section 08 and 09 published (100+ videos for the last two sections)! -* 30 Aug 2022 - recorded 15 videos for 09, total videos: 321, finished section 09 videos!!!! ... even bigger than 08!! -* 29 Aug 2022 - recorded 16 videos for 09, total videos: 306 -* 28 Aug 2022 - recorded 11 videos for 09, total videos: 290 -* 27 Aug 2022 - recorded 16 videos for 09, total videos: 279 -* 26 Aug 2022 - add finishing touchs to notebook 09, add slides for 09, create solutions and exercises for 09 -* 25 Aug 2022 - add annotations and cleanup 09, remove TK's, cleanup images, make slides for 09 -* 24 Aug 2022 - add annotations to 09, main takeaways, exercises and extra-curriculum done -* 23 Aug 2022 - add annotations to 09, add plenty of images/slides -* 22 Aug 2022 - add annotations to 09, start working on slides/images -* 20 Aug 2022 - add annotations to 09 -* 19 Aug 2022 - add annotations to 09, check out the awesome demos! -* 18 Aug 2022 - add annotations to 09 -* 17 Aug 2022 - add annotations to 09 -* 16 Aug 2022 - add annotations to 09 -* 15 Aug 2022 - add annotations to 09 -* 13 Aug 2022 - add annotations to 09 -* 12 Aug 2022 - add demo files for notebook 09 to `demos/`, start annotating notebook 09 with explainer text -* 11 Aug 2022 - finish skeleton code for notebook 09, course finishes deploying 2x models, one for FoodVision Mini & one for (secret) -* 10 Aug 2022 - add section for PyTorch Extra Resources (places to learn more about PyTorch/deep learning): https://www.learnpytorch.io/pytorch_extra_resources/ -* 09 Aug 2022 - add more skeleton code to notebook 09 -* 08 Aug 2022 - create draft notebook for 09, end goal to deploy FoodVision Mini model and make it publically accessible -* 05 Aug 2022 - recorded 11 videos for 08, total videos: 263, section 08 videos finished!... the biggest section so far -* 04 Aug 2022 - recorded 13 videos for 08, total videos: 252 -* 03 Aug 2022 - recorded 3 videos for 08, total videos: 239 -* 02 Aug 2022 - recorded 12 videos for 08, total videos: 236 -* 30 July 2022 - recorded 11 videos for 08, total videos: 224 -* 29 July 2022 - add exercises + solutions for 08, see live walkthrough on YouTube: https://youtu.be/tjpW_BY8y3g -* 28 July 2022 - add slides for 08 -* 27 July 2022 - cleanup much of 08, start on slides for 08, exercises and extra-curriculum next -* 26 July 2022 - add annotations and images for 08 -* 25 July 2022 - add annotations for 08 -* 24 July 2022 - launched first half of course (notebooks 00-04) in a single video (25+ hours!!!) on YouTube: https://youtu.be/Z_ikDlimN6A -* 21 July 2022 - add annotations and images for 08 -* 20 July 2022 - add annotations and images for 08, getting so close! this is an epic section -* 19 July 2022 - add annotations and images for 08 -* 15 July 2022 - add annotations and images for 08 -* 14 July 2022 - add annotations for 08 -* 12 July 2022 - add annotations for 08, woo woo this is bigggg section! -* 11 July 2022 - add annotations for 08 -* 9 July 2022 - add annotations for 08 -* 8 July 2022 - add a bunch of annotations to 08 -* 6 July 2022 - course launched on ZTM Academy with videos for sections 00-07! 🚀 - https://dbourke.link/ZTMPyTorch -* 1 July 2022 - add annotations and images for 08 -* 30 June 2022 - add annotations for 08 -* 28 June 2022 - recorded 11 videos for section 07, total video count 213, all videos for section 07 complete! -* 27 June 2022 - recorded 11 videos for section 07, total video count 202 -* 25 June 2022 - recreated 7 videos for section 06 to include updated APIs, total video count 191 -* 24 June 2022 - recreated 12 videos for section 06 to include updated APIs -* 23 June 2022 - finish annotations for 07, add exercise template and solutions for 07 + video walkthrough on YouTube: https://youtu.be/cO_r2FYcAjU -* 21 June 2022 - make 08 runnable end-to-end, add images and annotations for 07 -* 17 June 2022 - fix up 06, 07 v2 for upcoming torchvision version upgrade, add plenty of annotations to 08 -* 13 June 2022 - add notebook 08 first version, starting to replicate the Vision Transformer paper -* 10 June 2022 - add annotations for 07 v2 -* 09 June 2022 - create 07 v2 for `torchvision` v0.13 (this will replace 07 v1 when `torchvision=0.13` is released) -* 08 June 2022 - adapt 06 v2 for `torchvision` v0.13 (this will replace 06 v1 when `torchvision=0.13` is released) -* 07 June 2022 - create notebook 06 v2 for upcoming `torchvision` v0.13 update (new transfer learning methods) -* 04 June 2022 - add annotations for 07 -* 03 June 2022 - huuuuuuge amount of annotations added to 07 -* 31 May 2022 - add a bunch of annotations for 07, make code runnable end-to-end -* 30 May 2022 - record 4 videos for 06, finished section 06, onto section 07, total videos 186 -* 28 May 2022 - record 10 videos for 06, total videos 182 -* 24 May 2022 - add solutions and exercises for 06 -* 23 May 2022 - finished annotations and images for 06, time to do exercises and solutions -* 22 May 2202 - add plenty of images to 06 -* 18 May 2022 - add plenty of annotations to 06 -* 17 May 2022 - added a bunch of annotations for section 06 -* 16 May 2022 - recorded 10 videos for section 05, finish videos for section 05 ✅ -* 12 May 2022 - added exercises and solutions for 05 -* 11 May 2022 - clean up part 1 and part 2 notebooks for 05, make slides for 05, start on exercises and solutions for 05 -* 10 May 2022 - huuuuge updates to the 05 section, see the website, it looks pretty: https://www.learnpytorch.io/05_pytorch_going_modular/ -* 09 May 2022 - add a bunch of materials for 05, cleanup docs -* 08 May 2022 - add a bunch of materials for 05 -* 06 May 2022 - continue making materials for 05 -* 05 May 2022 - update section 05 with headings/outline -* 28 Apr 2022 - recorded 13 videos for 04, finished videos for 04, now to make materials for 05 -* 27 Apr 2022 - recorded 3 videos for 04 -* 26 Apr 2022 - recorded 10 videos for 04 -* 25 Apr 2022 - recorded 11 videos for 04 -* 24 Apr 2022 - prepared slides for 04 -* 23 Apr 2022 - recorded 6 videos for 03, finished videos for 03, now to 04 -* 22 Apr 2022 - recorded 5 videos for 03 -* 21 Apr 2022 - recorded 9 videos for 03 -* 20 Apr 2022 - recorded 3 videos for 03 -* 19 Apr 2022 - recorded 11 videos for 03 -* 18 Apr 2022 - finish exercises/solutions for 04, added live-coding walkthrough of 04 exercises/solutions on YouTube: https://youtu.be/vsFMF9wqWx0 -* 16 Apr 2022 - finish exercises/solutions for 03, added live-coding walkthrough of 03 exercises/solutions on YouTube: https://youtu.be/_PibmqpEyhA -* 14 Apr 2022 - add final images/annotations for 04, begin on exercises/solutions for 03 & 04 -* 13 Apr 2022 - add more images/annotations for 04 -* 3 Apr 2022 - add more annotations for 04 -* 2 Apr 2022 - add more annotations for 04 -* 1 Apr 2022 - add more annotations for 04 -* 31 Mar 2022 - add more annotations for 04 -* 29 Mar 2022 - add more annotations for 04 -* 27 Mar 2022 - starting to add annotations for 04 -* 26 Mar 2022 - making dataset for 04 -* 25 Mar 2022 - make slides for 03 -* 24 Mar 2022 - fix error for 03 not working in docs (finally) -* 23 Mar 2022 - add more images for 03 -* 22 Mar 2022 - add images for 03 -* 20 Mar 2022 - add more annotations for 03 -* 18 Mar 2022 - add more annotations for 03 -* 17 Mar 2022 - add more annotations for 03 -* 16 Mar 2022 - add more annotations for 03 -* 15 Mar 2022 - add more annotations for 03 -* 14 Mar 2022 - start adding annotations for notebook 03, see the work in progress here: https://www.learnpytorch.io/03_pytorch_computer_vision/ -* 12 Mar 2022 - recorded 12 videos for 02, finished section 02, now onto making materials for 03, 04, 05 -* 11 Mar 2022 - recorded 9 videos for 02 -* 10 Mar 2022 - recorded 10 videos for 02 -* 9 Mar 2022 - cleaning up slides/code for 02, getting ready for recording -* 8 Mar 2022 - recorded 9 videos for section 01, finished section 01, now onto 02 -* 7 Mar 2022 - recorded 4 videos for section 01 -* 6 Mar 2022 - recorded 4 videos for section 01 -* 4 Mar 2022 - recorded 10 videos for section 01 -* 20 Feb 2022 - recorded 8 videos for section 00, finished section, now onto 01 -* 18 Feb 2022 - recorded 13 videos for section 00 -* 17 Feb 2022 - recorded 11 videos for section 00 -* 16 Feb 2022 - added setup guide -* 12 Feb 2022 - tidy up README with table of course materials, finish images and slides for 01 -* 10 Feb 2022 - finished slides and images for 00, notebook is ready for publishing: https://www.learnpytorch.io/00_pytorch_fundamentals/ -* 01-07 Feb 2022 - add annotations for 02, finished, still need images, going to work on exercises/solutions today -* 31 Jan 2022 - start adding annotations for 02 -* 28 Jan 2022 - add exercies and solutions for 01 -* 26 Jan 2022 - lots more annotations to 01, should be finished tomorrow, will do exercises + solutions then too -* 24 Jan 2022 - add a bunch of annotations to 01 -* 21 Jan 2022 - start adding annotations for 01 -* 20 Jan 2022 - finish annotations for 00 (still need to add images), add exercises and solutions for 00 -* 19 Jan 2022 - add more annotations for 00 -* 18 Jan 2022 - add more annotations for 00 -* 17 Jan 2022 - back from holidays, adding more annotations to 00 -* 10 Dec 2021 - start adding annotations for 00 -* 9 Dec 2021 - Created a website for the course ([learnpytorch.io](https://learnpytorch.io)) you'll see updates posted there as development continues -* 8 Dec 2021 - Clean up notebook 07, starting to go back through code and add annotations -* 26 Nov 2021 - Finish skeleton code for 07, added four different experiments, need to clean up and make more straightforward -* 25 Nov 2021 - clean code for 06, add skeleton code for 07 (experiment tracking) -* 24 Nov 2021 - Update 04, 05, 06 notebooks for easier digestion and learning, each section should cover a max of 3 big ideas, 05 is now dedicated to turning notebook code into modular code -* 22 Nov 2021 - Update 04 train and test functions to make more straightforward -* 19 Nov 2021 - Added 05 (transfer learning) notebook, update custom data loading code in 04 -* 18 Nov 2021 - Updated vision code for 03 and added custom dataset loading code in 04 -* 12 Nov 2021 - Added a bunch of skeleton code to notebook 04 for custom dataset loading, next is modelling with custom data -* 10 Nov 2021 - researching best practice for custom datasets for 04 -* 9 Nov 2021 - Update 03 skeleton code to finish off building CNN model, onto 04 for loading custom datasets -* 4 Nov 2021 - Add GPU code to 03 + train/test loops + `helper_functions.py` -* 3 Nov 2021 - Add basic start for 03, going to finish by end of week -* 29 Oct 2021 - Tidied up skeleton code for 02, still a few more things to clean/tidy, created 03 -* 28 Oct 2021 - Finished skeleton code for 02, going to clean/tidy tomorrow, 03 next week -* 27 Oct 2021 - add a bunch of code for 02, going to finish tomorrow/by end of week -* 26 Oct 2021 - update 00, 01, 02 with outline/code, skeleton code for 00 & 01 done, 02 next -* 23, 24 Oct 2021 - update 00 and 01 notebooks with more outline/code -* 20 Oct 2021 - add v0 outlines for 01 and 02, add rough outline of course to README, this course will focus on less but better -* 19 Oct 2021 - Start repo 🔥, add fundamentals notebook draft v0 +* 15 May 2023 - PyTorch 2.0 教程完成 + 视频已添加到 ZTM/Udemy，见代码：https://www.learnpytorch.io/pytorch_2_intro/ +* 13 Apr 2023 - 更新 PyTorch 2.0 notebook +* 30 Mar 2023 - 更新 PyTorch 2.0 notebook，补充更多信息/清理代码 +* 23 Mar 2023 - 升级 PyTorch 2.0 教程，添加注释和图片 +* 13 Mar 2023 - 为 PyTorch 2.0 教程添加入门代码 +* 18 Nov 2022 - 添加 PyTorch 3 个最常见错误的参考 + 更多课程章节链接：https://www.learnpytorch.io/pytorch_most_common_errors/ +* 9 Nov 2022 - 添加 PyTorch cheatsheet，快速概览 PyTorch 主要特性 + 课程章节链接：https://www.learnpytorch.io/pytorch_cheatsheet/ +* 9 Nov 2022 - 完整课程材料（300+ 个视频）现已在 Udemy 上线！可在此注册：https://www.udemy.com/course/pytorch-for-deep-learning/?couponCode=ZTMGOODIES7（上线优惠码自本条起 3–4 天内有效） +* 4 Nov 2022 - 在 `extras/` 中添加 PyTorch Cheatsheet 的 notebook（简要概览 PyTorch 许多最重要功能） +* 2 Oct 2022 - 第 08 和 09 节的所有视频已发布（最后两节 100+ 个视频）！ +* 30 Aug 2022 - 为 09 录制 15 个视频，视频总数：321，第 09 节视频完成！！！……甚至比 08 还大！！ +* 29 Aug 2022 - 为 09 录制 16 个视频，视频总数：306 +* 28 Aug 2022 - 为 09 录制 11 个视频，视频总数：290 +* 27 Aug 2022 - 为 09 录制 16 个视频，视频总数：279 +* 26 Aug 2022 - 为 notebook 09 做收尾，添加 09 的 slides，创建 09 的 solutions 和 exercises +* 25 Aug 2022 - 为 09 添加注释并清理，移除 TK's，清理图片，制作 09 的 slides +* 24 Aug 2022 - 为 09 添加注释，main takeaways、exercises 和 extra-curriculum 完成 +* 23 Aug 2022 - 为 09 添加注释，添加大量图片/slides +* 22 Aug 2022 - 为 09 添加注释，开始制作 slides/图片 +* 20 Aug 2022 - 为 09 添加注释 +* 19 Aug 2022 - 为 09 添加注释，看看这些很棒的 demos！ +* 18 Aug 2022 - 为 09 添加注释 +* 17 Aug 2022 - 为 09 添加注释 +* 16 Aug 2022 - 为 09 添加注释 +* 15 Aug 2022 - 为 09 添加注释 +* 13 Aug 2022 - 为 09 添加注释 +* 12 Aug 2022 - 将 notebook 09 的 demo 文件添加到 `demos/`，开始为 notebook 09 添加说明文字注释 +* 11 Aug 2022 - 完成 notebook 09 的骨架代码，课程完成部署 2 个模型，一个用于 FoodVision Mini，另一个用于（secret） +* 10 Aug 2022 - 添加 PyTorch Extra Resources 章节（学习更多 PyTorch/深度学习的去处）：https://www.learnpytorch.io/pytorch_extra_resources/ +* 09 Aug 2022 - 为 notebook 09 添加更多骨架代码 +* 08 Aug 2022 - 创建 09 的草稿 notebook，最终目标是部署 FoodVision Mini 模型并使其公开可访问 +* 05 Aug 2022 - 为 08 录制 11 个视频，视频总数：263，第 08 节视频完成！……目前为止最大的一节 +* 04 Aug 2022 - 为 08 录制 13 个视频，视频总数：252 +* 03 Aug 2022 - 为 08 录制 3 个视频，视频总数：239 +* 02 Aug 2022 - 为 08 录制 12 个视频，视频总数：236 +* 30 July 2022 - 为 08 录制 11 个视频，视频总数：224 +* 29 July 2022 - 为 08 添加 exercises + solutions，见 YouTube 上的 live walkthrough：https://youtu.be/tjpW_BY8y3g +* 28 July 2022 - 为 08 添加 slides +* 27 July 2022 - 清理 08 的大部分内容，开始制作 08 的 slides，接下来做 exercises 和 extra-curriculum +* 26 July 2022 - 为 08 添加注释和图片 +* 25 July 2022 - 为 08 添加注释 +* 24 July 2022 - 在 YouTube 上以单个视频（25+ 小时！！！）发布课程前半部分（notebooks 00–04）：https://youtu.be/Z_ikDlimN6A +* 21 July 2022 - 为 08 添加注释和图片 +* 20 July 2022 - 为 08 添加注释和图片，越来越近了！这是史诗级的一节 +* 19 July 2022 - 为 08 添加注释和图片 +* 15 July 2022 - 为 08 添加注释和图片 +* 14 July 2022 - 为 08 添加注释 +* 12 July 2022 - 为 08 添加注释，woo woo 这是超大大的一节！ +* 11 July 2022 - 为 08 添加注释 +* 9 July 2022 - 为 08 添加注释 +* 8 July 2022 - 为 08 添加大量注释 +* 6 July 2022 - 课程在 ZTM Academy 上线，包含第 00–07 节的视频！🚀 - https://dbourke.link/ZTMPyTorch +* 1 July 2022 - 为 08 添加注释和图片 +* 30 June 2022 - 为 08 添加注释 +* 28 June 2022 - 为第 07 节录制 11 个视频，视频总数 213，第 07 节所有视频完成！ +* 27 June 2022 - 为第 07 节录制 11 个视频，视频总数 202 +* 25 June 2022 - 为第 06 节重录 7 个视频以包含更新后的 API，视频总数 191 +* 24 June 2022 - 为第 06 节重录 12 个视频以包含更新后的 API +* 23 June 2022 - 完成 07 的注释，为 07 添加 exercise template 和 solutions + YouTube 上的 video walkthrough：https://youtu.be/cO_r2FYcAjU +* 21 June 2022 - 使 08 可端到端运行，为 07 添加图片和注释 +* 17 June 2022 - 修复 06、07 v2 以适配即将发布的 torchvision 版本升级，为 08 添加大量注释 +* 13 June 2022 - 添加 notebook 08 第一版，开始复现 Vision Transformer 论文 +* 10 June 2022 - 为 07 v2 添加注释 +* 09 June 2022 - 为 `torchvision` v0.13 创建 07 v2（当 `torchvision=0.13` 发布后将替换 07 v1） +* 08 June 2022 - 为 `torchvision` v0.13 适配 06 v2（当 `torchvision=0.13` 发布后将替换 06 v1） +* 07 June 2022 - 为即将发布的 `torchvision` v0.13 更新创建 notebook 06 v2（新的 transfer learning 方法） +* 04 June 2022 - 为 07 添加注释 +* 03 June 2022 - 为 07 添加海量注释 +* 31 May 2022 - 为 07 添加大量注释，使代码可端到端运行 +* 30 May 2022 - 为 06 录制 4 个视频，完成第 06 节，进入第 07 节，视频总数 186 +* 28 May 2022 - 为 06 录制 10 个视频，视频总数 182 +* 24 May 2022 - 为 06 添加 solutions 和 exercises +* 23 May 2022 - 完成 06 的注释和图片，该做 exercises 和 solutions 了 +* 22 May 2202 - 为 06 添加大量图片 +* 18 May 2022 - 为 06 添加大量注释 +* 17 May 2022 - 为第 06 节添加大量注释 +* 16 May 2022 - 为第 05 节录制 10 个视频，完成第 05 节视频 ✅ +* 12 May 2022 - 为 05 添加 exercises 和 solutions +* 11 May 2022 - 清理 05 的 part 1 和 part 2 notebooks，制作 05 的 slides，开始做 05 的 exercises 和 solutions +* 10 May 2022 - 对 05 节进行海量更新，见网站，看起来很漂亮：https://www.learnpytorch.io/05_pytorch_going_modular/ +* 09 May 2022 - 为 05 添加大量材料，清理文档 +* 08 May 2022 - 为 05 添加大量材料 +* 06 May 2022 - 继续制作 05 的材料 +* 05 May 2022 - 用标题/大纲更新第 05 节 +* 28 Apr 2022 - 为 04 录制 13 个视频，完成第 04 节视频，现在制作 05 的材料 +* 27 Apr 2022 - 为 04 录制 3 个视频 +* 26 Apr 2022 - 为 04 录制 10 个视频 +* 25 Apr 2022 - 为 04 录制 11 个视频 +* 24 Apr 2022 - 为 04 准备 slides +* 23 Apr 2022 - 为 03 录制 6 个视频，完成第 03 节视频，现在进入 04 +* 22 Apr 2022 - 为 03 录制 5 个视频 +* 21 Apr 2022 - 为 03 录制 9 个视频 +* 20 Apr 2022 - 为 03 录制 3 个视频 +* 19 Apr 2022 - 为 03 录制 11 个视频 +* 18 Apr 2022 - 完成 04 的 exercises/solutions，在 YouTube 上添加 04 exercises/solutions 的 live-coding walkthrough：https://youtu.be/vsFMF9wqWx0 +* 16 Apr 2022 - 完成 03 的 exercises/solutions，在 YouTube 上添加 03 exercises/solutions 的 live-coding walkthrough：https://youtu.be/_PibmqpEyhA +* 14 Apr 2022 - 为 04 添加最终图片/注释，开始制作 03 和 04 的 exercises/solutions +* 13 Apr 2022 - 为 04 添加更多图片/注释 +* 3 Apr 2022 - 为 04 添加更多注释 +* 2 Apr 2022 - 为 04 添加更多注释 +* 1 Apr 2022 - 为 04 添加更多注释 +* 31 Mar 2022 - 为 04 添加更多注释 +* 29 Mar 2022 - 为 04 添加更多注释 +* 27 Mar 2022 - 开始为 04 添加注释 +* 26 Mar 2022 - 为 04 制作 dataset +* 25 Mar 2022 - 为 03 制作 slides +* 24 Mar 2022 - 修复 03 在 docs 中无法运行的问题（终于） +* 23 Mar 2022 - 为 03 添加更多图片 +* 22 Mar 2022 - 为 03 添加图片 +* 20 Mar 2022 - 为 03 添加更多注释 +* 18 Mar 2022 - 为 03 添加更多注释 +* 17 Mar 2022 - 为 03 添加更多注释 +* 16 Mar 2022 - 为 03 添加更多注释 +* 15 Mar 2022 - 为 03 添加更多注释 +* 14 Mar 2022 - 开始为 notebook 03 添加注释，见进行中的工作：https://www.learnpytorch.io/03_pytorch_computer_vision/ +* 12 Mar 2022 - 为 02 录制 12 个视频，完成第 02 节，现在制作 03、04、05 的材料 +* 11 Mar 2022 - 为 02 录制 9 个视频 +* 10 Mar 2022 - 为 02 录制 10 个视频 +* 9 Mar 2022 - 清理 02 的 slides/code，准备录制 +* 8 Mar 2022 - 为第 01 节录制 9 个视频，完成第 01 节，现在进入 02 +* 7 Mar 2022 - 为第 01 节录制 4 个视频 +* 6 Mar 2022 - 为第 01 节录制 4 个视频 +* 4 Mar 2022 - 为第 01 节录制 10 个视频 +* 20 Feb 2022 - 为第 00 节录制 8 个视频，完成该节，现在进入 01 +* 18 Feb 2022 - 为第 00 节录制 13 个视频 +* 17 Feb 2022 - 为第 00 节录制 11 个视频 +* 16 Feb 2022 - 添加 setup guide +* 12 Feb 2022 - 整理 README，添加课程材料表格，完成 01 的图片和 slides +* 10 Feb 2022 - 完成 00 的 slides 和图片，notebook 已可发布：https://www.learnpytorch.io/00_pytorch_fundamentals/ +* 01-07 Feb 2022 - 为 02 添加注释，已完成，仍需要图片，今天将做 exercises/solutions +* 31 Jan 2022 - 开始为 02 添加注释 +* 28 Jan 2022 - 为 01 添加 exercies 和 solutions +* 26 Jan 2022 - 为 01 添加更多注释，明天应该能完成，之后也会做 exercises + solutions +* 24 Jan 2022 - 为 01 添加大量注释 +* 21 Jan 2022 - 开始为 01 添加注释 +* 20 Jan 2022 - 完成 00 的注释（仍需添加图片），为 00 添加 exercises 和 solutions +* 19 Jan 2022 - 为 00 添加更多注释 +* 18 Jan 2022 - 为 00 添加更多注释 +* 17 Jan 2022 - 假期回来，为 00 添加更多注释 +* 10 Dec 2021 - 开始为 00 添加注释 +* 9 Dec 2021 - 为课程创建网站（[learnpytorch.io](https://learnpytorch.io)) 随着开发推进，你会在那里看到更新发布 +* 8 Dec 2021 - 清理 notebook 07，开始回头检查代码并添加注释 +* 26 Nov 2021 - 完成 07 的骨架代码，添加了四个不同实验，需要清理并使其更直观 +* 25 Nov 2021 - 清理 06 的代码，为 07 添加骨架代码（experiment tracking） +* 24 Nov 2021 - 更新 04、05、06 notebooks 以便更易消化和学习，每节最多涵盖 3 个大概念，05 现在专门用于将 notebook 代码转为模块化代码 +* 22 Nov 2021 - 更新 04 的 train 和 test 函数，使其更直观 +* 19 Nov 2021 - 添加 05（transfer learning）notebook，更新 04 中的 custom data loading 代码 +* 18 Nov 2021 - 更新 03 的 vision 代码，并在 04 中添加 custom dataset loading 代码 +* 12 Nov 2021 - 为 notebook 04 添加大量 custom dataset loading 的骨架代码，下一步是用 custom data 建模 +* 10 Nov 2021 - 为 04 研究 custom datasets 的最佳实践 +* 9 Nov 2021 - 更新 03 骨架代码以完成 CNN model 构建，接下来进入 04 加载 custom datasets +* 4 Nov 2021 - 为 03 添加 GPU 代码 + train/test loops + `helper_functions.py` +* 3 Nov 2021 - 为 03 添加基础起步，计划本周末完成 +* 29 Oct 2021 - 整理 02 的骨架代码，仍有一些需要清理/整理，创建了 03 +* 28 Oct 2021 - 完成 02 的骨架代码，明天将清理/整理，下周做 03 +* 27 Oct 2021 - 为 02 添加大量代码，计划明天/本周末完成 +* 26 Oct 2021 - 用大纲/代码更新 00、01、02，00 和 01 的骨架代码完成，接下来是 02 +* 23, 24 Oct 2021 - 用更多大纲/代码更新 00 和 01 notebooks +* 20 Oct 2021 - 为 01 和 02 添加 v0 大纲，在 README 中添加课程粗略大纲，本课程将聚焦更少但更好的内容 +* 19 Oct 2021 - 启动仓库 🔥，添加 fundamentals notebook 草稿 v0