{ "source_file": "0930", "source_platform": "研究机构", "author": "fast.ai", "title_listed": "Practical Deep Learning for Coders（免费课程）", "keywords": "深度学习,CV,NLP", "domain": "机器学习", "content_type": "课程", "is_paid_flag": "否", "url": "https://course.fast.ai", "publish_date": "持续更新", "corpus_stage": "机器学习", "notes": "fast.ai 旗舰免费课程", "id": "4f7dd672289b", "collected_at": "2026-10-02T16:04:04", "title": "Practical Deep Learning for Coders - Practical Deep Learning", "body_markdown": "Practical Deep Learning\nA free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.\nNew!\nWe just launched a new >30 hour video course for more experienced students:\nPractical Deep Learning for Coders part 2:\nDeep Learning Foundations to Stable Diffusion\nThis free course is designed for people (and bunnies!) with some coding experience who want to learn how to apply deep learning and machine learning to practical problems.\nDeep learning can do all kinds of amazing things. For instance, all illustrations throughout this website are made with deep learning, using\nDALL-E 2\n.\nWelcome!\nPractical Deep Learning for Coders 2022 part 1, recorded at the\nUniversity of Queensland\n, covers topics such as how to:\nBuild and train deep learning models for computer vision, natural language processing, tabular analysis, and collaborative filtering problems\nCreate random forests and regression models\nDeploy models\nUse PyTorch, the world’s fastest growing deep learning software, plus popular libraries like fastai and Hugging Face\nThere are 9 lessons, and each lesson is around 90 minutes long. The course is based on our\n5-star rated book\n, which is\nfreely available\nonline.\nYou don’t need any special hardware or software — we’ll show you how to use free resources for both building and deploying models. You don’t need any university math either — we’ll teach you the calculus and linear algebra you need during the course.\nGet started\nStart watching\nlesson 1\nnow!\nReal results\nOur videos have been viewed over 6,000,000 times already! Take a look at the\ndozens of testimonials\nabout our book and course by alumni, top academics, and industry experts.\n‘Deep Learning is for everyone’ we see in Chapter 1, Section 1 of this book, and while other books may make similar claims, this book delivers on the claim. The authors have extensive knowledge of the field but are able to describe it in a way that is perfectly suited for a reader with experience in programming but not in machine learning. The book shows examples first, and only covers theory in the context of concrete examples. For most people, this is the best way to learn. The book does an impressive job of covering the key applications of deep learning in computer vision, natural language processing, and tabular data processing, but also covers key topics like data ethics that some other books miss. Altogether, this is one of the best sources for a programmer to become proficient in deep learning.\nPeter Norvig\nDirector of Research, Google\nBy the end of the second lesson, you will have built and deployed your own deep learning model on data you collect. Many students post their course projects to our forum; you can\nview them here\n. For instance, if there’s an unknown dinosaur in your backyard, maybe you need this\ndinosaur classifier\n!\nAlumni of our course have gone on to jobs at organizations like\nGoogle Brain\n,\nOpenAI\n,\nAdobe\n,\nAmazon\n, and\nTesla\n, published research at top conferences such as\nNeurIPS\n, and created startups using skills they learned here. Petro Cuenca, lead developer of the widely-acclaimed\nCamera+\napp, after completing the course went on to add deep learning features to his product, which was then\nfeatured by Apple\nfor its “machine learning magic”.\nGet started\nStart watching\nlesson 1\nnow!\nYour teacher\nI am Jeremy Howard, your guide on this journey. I lead the development of fastai, the software that you’ll be using throughout this course. I have been using and teaching machine learning for around 30 years. I was the top-ranked competitor globally in machine learning competitions on Kaggle (the world’s largest machine learning community) two years running. Following this success, I became the President and Chief Scientist of Kaggle. Since first using neural networks 25 years ago, I have led many companies and projects that have machine learning at their core, including founding the first company to focus on deep learning and medicine, Enlitic (chosen by MIT Tech Review as one of the “world’s smartest companies”).\nJeremy Howard\nI am the co-founder, along with Dr. Rachel Thomas, of fast.ai, the organization behind this course. At fast.ai we care a lot about teaching. In this course, I start by showing how to use a complete, working, very usable, state-of-the-art deep learning network to solve real-world problems, using simple, expressive tools. And then we gradually dig deeper and deeper into understanding how those tools are made, and how the tools that make those tools are made, and so on… We always teach through examples. We ensure that there is a context and a purpose that you can understand intuitively, rather than starting with algebraic symbol manipulation.\nGet started\nStart watching\nlesson 1\nnow!\nIs this course for me?\nPrevious fast.ai courses have been studied by hundreds of thousands of students, from all walks of life, from all parts of the world. Many students have told us about how they’ve become\nmultiple gold medal winners\nof\ninternational machine learning competitions\n,\nreceived offers\nfrom top companies, and having\nresearch\npapers\npublished\n. For instance, Isaac Dimitrovsky\ntold us\nthat he had “\nbeen playing around with ML for a couple of years without really grokking it… [then] went through the fast.ai part 1 course late last year, and it clicked for me\n”. He went on to achieve first place in the prestigious international\nRA2-DREAM Challenge\ncompetition! He developed a\nmultistage deep learning method\nfor scoring radiographic hand and foot joint damage in rheumatoid arthritis, taking advantage of the fastai library.\nIt doesn’t matter if you don’t come from a technical or a mathematical background (though it’s okay if you do too!); we wrote this course to make deep learning accessible to as many people as possible. The only prerequisite is that you know how to code (a year of experience is enough), preferably in Python, and that you have at least followed a high school math course.\nDeep learning is a computer technique to extract and transform data–-with use cases ranging from human speech recognition to animal imagery classification–-by using multiple layers of neural networks. A lot of people assume that you need all kinds of hard-to-find stuff to get great results with deep learning, but as you’ll see in this course, those people are wrong. Here’s a few things you\nabsolutely don’t need\nto do world-class deep learning:\nMyth (don’t need)\nTruth\nLots of math\nJust high school math is sufficient\nLots of data\nWe’ve seen record-breaking results with <50 items of data\nLots of expensive computers\nYou can get what you need for state of the art work for free\nGet started\nStart watching\nlesson 1\nnow!\nThe software you will be using\nIn this course, you’ll be using\nPyTorch\n,\nfastai\n, Hugging Face\nTransformers\n, and\nGradio\n.\nWe’ve completed hundreds of machine learning projects using dozens of different packages, and many different programming languages. At fast.ai, we have written courses using most of the main deep learning and machine learning packages used today. We spent over a thousand hours testing PyTorch before deciding that we would use it for future courses, software development, and research. PyTorch is now the world’s fastest-growing deep learning library and is already used for most research papers at top conferences.\nPyTorch works best as a low-level foundation library, providing the basic operations for higher-level functionality. The fastai library one of the most popular libraries for adding this higher-level functionality on top of PyTorch. In this course, as we go deeper and deeper into the foundations of deep learning, we will also go deeper and deeper into the layers of fastai.\nTransformers is a popular library focused on natural language processing (NLP) using\ntransformers models\n. In the course you’ll see how to create a cutting-edge transfomers model using this library to detect similar concepts in patent applications.\nGet started\nStart watching\nlesson 1\nnow!\nWhy deep learning?\nDeep learning has power, flexibility, and simplicity. That’s why we believe it should be applied across many disciplines. These include the social and physical sciences, the arts, medicine, finance, scientific research, and many more. Here’s a list of some of the thousands of tasks in different areas at which deep learning, or methods heavily using deep learning, is now the best in the world:\nNatural language processing (NLP)\nAnswering questions; speech recognition; summarizing documents; classifying documents; finding names, dates, etc. in documents; searching for articles mentioning a concept\nComputer vision\nSatellite and drone imagery interpretation (e.g., for disaster resilience); face recognition; image captioning; reading traffic signs; locating pedestrians and vehicles in autonomous vehicles\nMedicine\nFinding anomalies in radiology images, including CT, MRI, and X-ray images; counting features in pathology slides; measuring features in ultrasounds; diagnosing diabetic retinopathy\nBiology\nFolding proteins; classifying proteins; many genomics tasks, such as tumor-normal sequencing and classifying clinically actionable genetic mutations; cell classification; analyzing protein/protein interactions\nImage generation\nColorizing images; increasing image resolution; removing noise from images; converting images to art in the style of famous artists\nRecommendation systems\nWeb search; product recommendations; home page layout\nPlaying games\nChess, Go, most Atari video games, and many real-time strategy games\nRobotics\nHandling objects that are challenging to locate (e.g., transparent, shiny, lacking texture) or hard to pick up\nOther applications\nFinancial and logistical forecasting, text to speech, and much more…\nGet started\nStart watching\nlesson 1\nnow!\nWhat you will learn\nAfter finishing this course you will know:\nHow to train models that achieve state-of-the-art results in:\nComputer vision, including image classification (e.g., classifying pet photos by breed)\nNatural language processing (NLP), including document classification (e.g., movie review sentiment analysis) and phrase similarity\nTabular data with categorical data, continuous data, and mixed data\nCollaborative filtering (e.g., movie recommendation)\nHow to turn your models into web applications, and deploy them\nWhy and how deep learning models work, and how to use that knowledge to improve the accuracy, speed, and reliability of your models\nThe latest deep learning techniques that really matter in practice\nHow to implement stochastic gradient descent and a complete training loop from scratch\nHere are some of the techniques covered (don’t worry if none of these words mean anything to you yet–you’ll learn them all soon):\nRandom forests and gradient boosting\nAffine functions and nonlinearities\nParameters and activations\nTransfer learning\nStochastic gradient descent (SGD)\nData augmentation\nWeight decay\nImage classification\nEntity and word embeddings\nAnd much more\nGet started\nStart watching\nlesson 1\nnow!\nHow do I get started?\nTo watch the videos, click on the\nLessons\nsection in the navigation sidebar. The videos are all captioned; while watching the video click the “CC” button to turn them on and off. To get a sense of what’s covered in a lesson, you might want to skim through some lesson notes taken by one of our students (thanks Daniel!). Here’s his\nlesson 7 notes\nand\nlesson 8 notes\n. You can also access all the videos through\nthis YouTube playlist\n.\nEach video is designed to go with various chapters from the book. The entirety of every chapter of the book is available as an interactive Jupyter Notebook.\nJupyter Notebook\nis the most popular tool for doing data science in Python, for good reason. It is powerful, flexible, and easy to use. We think you will love it! Since the most important thing for learning deep learning is writing code and experimenting, it’s important that you have a great platform for experimenting with code.\nWe’ll mainly use\nKaggle Notebooks\nand\nPaperspace Gradient\nbecause we’ve found they work really well for this course, and have good free options. We also will do some parts of the course on your own laptop. (If you don’t have a Paperspace account yet, sign up with\nthis link\nto get $10 credit – and we get a credit too.)\nWe strongly suggest\nnot\nusing your own computer for training models in this course, unless you’re very experienced with Linux system adminstration and handling GPU drivers, CUDA, and so forth.\nIf you need help, there’s a\nwonderful online community\nready to help you at forums.fast.ai. Before asking a question on the forums, search carefully to see if your question has been answered before.\nGet started\nStart watching\nlesson 1\nnow!", "metadata": { "title": "Practical Deep Learning for Coders - Practical Deep Learning", "description": "A free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.", "keywords": null, "author": null, "og:title": "Practical Deep Learning for Coders - Practical Deep Learning", "og:description": "A free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.", "og:image": "https://course.fast.ai/www/social.png", "og:site_name": "Practical Deep Learning for Coders", "twitter:title": "Practical Deep Learning for Coders - Practical Deep Learning", "twitter:description": "A free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.", "twitter:image": "https://course.fast.ai/www/social.png", "twitter:card": "summary_large_image" }, "paywall": { "listed_paid": false, "detected": false, "marker": "", "public_only": false, "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙" }, "crawl": { "success": true, "status_code": 200, "error": "" }, "code_blocks": [], "images": [ { "status": "ok", "url": "https://course.fast.ai/images/pencil_sketch.png", "bytes": 351533, "reused": false, "local_path": "attachments/4f7dd672289b/images/body-6d9763460550670f37b4.png", "src": "https://course.fast.ai/images/pencil_sketch.png", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://course.fast.ai/images/imagine.png", "bytes": 342225, "reused": false, "local_path": "attachments/4f7dd672289b/images/body-a576897af130cfb47063.png", "src": "https://course.fast.ai/images/imagine.png", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://course.fast.ai/images/people/norvig.jpg", "bytes": 60458, "reused": false, "local_path": "attachments/4f7dd672289b/images/body-4d414f83921a02be9595.jpg", "src": "https://course.fast.ai/images/people/norvig.jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://user-images.githubusercontent.com/346999/177054810-3e56fcb1-4fb7-418a-b10b-351bab20bf6b.png", "bytes": 749772, "reused": true, "local_path": "attachments/4f7dd672289b/images/003.png", "src": "https://user-images.githubusercontent.com/346999/177054810-3e56fcb1-4fb7-418a-b10b-351bab20bf6b.png", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://course.fast.ai/images/people/jeremy.jpg", "bytes": 43520, "reused": false, "local_path": "attachments/4f7dd672289b/images/body-c9fbf81fad3dfbd3062a.jpg", "src": "https://course.fast.ai/images/people/jeremy.jpg", "alt": "", "downloaded": true } ], "audio": [], "videos": [ { "url": "https://www.youtube.com/playlist?list=PLfYUBJiXbdtSvpQjSnJJ_PmDQB_VyT5iU", "src": "https://www.youtube.com/playlist?list=PLfYUBJiXbdtSvpQjSnJJ_PmDQB_VyT5iU", "status": "ok", "kind": "playlist", "items": [ { "url": "https://www.youtube.com/watch?v=8SF_h3xF3cE", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/4f7dd672289b/videos/repair-8SF_h3xF3cE.mp4", "bytes": 293001647, "valid": true, "height": 1080, "width": 1920, "duration": "4975.261000", "reused": false, "retried_at": "2026-10-18T18:02:29Z" }, { "url": "https://www.youtube.com/watch?v=F4tvM4Vb3A0", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/4f7dd672289b/videos/repair-F4tvM4Vb3A0.mp4", "bytes": 310243014, "valid": true, "height": 1080, "width": 1920, "duration": "4601.581000", "reused": false, "retried_at": "2026-10-18T18:02:27Z" }, { "url": "https://www.youtube.com/watch?v=hBBOjCiFcuo", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/4f7dd672289b/videos/repair-hBBOjCiFcuo.mp4", "bytes": 407997078, "valid": true, "height": 1080, "width": 1920, "duration": "5424.301000", "reused": false, "retried_at": "2026-10-18T18:02:49Z" }, { "url": "https://www.youtube.com/watch?v=toUgBQv1BT8", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/4f7dd672289b/videos/repair-toUgBQv1BT8.mp4", "bytes": 309377711, "valid": true, "height": 1080, "width": 1920, "duration": "5676.501000", "reused": false, "retried_at": "2026-10-18T18:03:26Z" }, { "url": "https://www.youtube.com/watch?v=_rXzeWq4C6w", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/4f7dd672289b/videos/repair-_rXzeWq4C6w.mp4", "bytes": 338337810, "valid": true, "height": 1080, "width": 1920, "duration": "6168.201000", "reused": false, "retried_at": "2026-10-18T18:03:13Z" }, { "url": "https://www.youtube.com/watch?v=AdhG64NF76E", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/4f7dd672289b/videos/repair-AdhG64NF76E.mp4", "bytes": 671773463, "valid": true, "height": 1080, "width": 1920, "duration": "6174.101000", "reused": false, "retried_at": "2026-10-18T18:03:44Z" }, { "url": "https://www.youtube.com/watch?v=p4ZZq0736Po", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/4f7dd672289b/videos/repair-p4ZZq0736Po.mp4", "bytes": 518992591, "valid": true, "height": 1080, "width": 1920, "duration": "6402.301000", "reused": false, "retried_at": "2026-10-18T18:03:39Z" }, { "url": "https://www.youtube.com/watch?v=htiNBPxcXgo", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/4f7dd672289b/videos/repair-htiNBPxcXgo.mp4", "bytes": 1146686227, "valid": true, "height": 1080, "width": 1920, "duration": "5814.721000", "reused": false, "retried_at": "2026-10-18T18:04:19Z" } ], "retried_at": "2026-10-18T17:07:25Z" } ], "links": [ { "href": "https://course.fast.ai/Lessons/part2.html", "label": "Practical Deep Learning for Coders part 2: Deep Learning Foundations to Stable Diffusion", "type": "a" }, { "href": "https://openai.com/dall-e-2/", "label": "DALL-E 2", "type": "a" }, { "href": "https://www.uq.edu.au/", "label": "University of Queensland", "type": "a" }, { "href": "https://www.amazon.com/Deep-Learning-Coders-fastai-PyTorch/dp/1492045527", "label": "5-star rated book", "type": "a" }, { "href": "https://course.fast.ai/Resources/book.html", "label": "freely available", "type": "a" }, { "href": "https://course.fast.ai/Lessons/lesson1.html", "label": "lesson 1", "type": "a" }, { "href": "https://course.fast.ai/Resources/testimonials.html", "label": "dozens of testimonials", "type": "a" }, { "href": "https://forums.fast.ai/t/share-your-work-here/96015", "label": "view them here", "type": "a" }, { "href": "https://notebooksg.jarvislabs.ai/U7mQvWgvra53-YvTogLgJCfNzgJxRJv238Go2bHoAmHBqQFHoOL1ZFeKDG8gYmnO/", "label": "dinosaur classifier", "type": "a" }, { "href": "https://en.wikipedia.org/wiki/Conference_on_Neural_Information_Processing_Systems", "label": "NeurIPS", "type": "a" }, { "href": "https://camera.plus/", "label": "Camera+", "type": "a" }, { "href": "https://twitter.com/pcuenq/status/1540121042596904963", "label": "featured by Apple", "type": "a" }, { "href": "https://forums.fast.ai/t/my-first-gold-medal/54237", "label": "multiple gold medal winners", "type": "a" }, { "href": "https://towardsdatascience.com/my-3-year-journey-from-zero-python-to-deep-learning-competition-master-6605c188eec7", "label": "international machine learning competitions", "type": "a" }, { "href": "https://forums.fast.ai/t/how-has-your-journey-been-so-far-learners/6480/2", "label": "received offers", "type": "a" }, { "href": "https://ui.adsabs.harvard.edu/abs/2020EGUGA..2221465A/abstract", "label": "research", "type": "a" }, { "href": "http://www.ieomsociety.org/ieom2020/papers/37.pdf", "label": "papers", "type": "a" }, { "href": "https://pubs.rsna.org/doi/abs/10.1148/ryai.2019190113?journalCode=ai", "label": "published", "type": "a" }, { "href": "https://forums.fast.ai/t/thanks-ra2-dream-challenge-win/76875", "label": "told us", "type": "a" }, { "href": "https://www.synapse.org/", "label": "RA2-DREAM Challenge", "type": "a" }, { "href": "https://pytorch.org/", "label": "PyTorch", "type": "a" }, { "href": "https://docs.fast.ai/", "label": "fastai", "type": "a" }, { "href": "https://huggingface.co/docs/transformers/index", "label": "Transformers", "type": "a" }, { "href": "https://gradio.app/", "label": "Gradio", "type": "a" }, { "href": "https://course.fast.ai/Lessons/Summaries/lesson7.html", "label": "lesson 7 notes", "type": "a" }, { "href": "https://course.fast.ai/Lessons/Summaries/lesson8.html", "label": "lesson 8 notes", "type": "a" }, { "href": "https://www.youtube.com/playlist?list=PLfYUBJiXbdtSvpQjSnJJ_PmDQB_VyT5iU", "label": "this YouTube playlist", "type": "a" }, { "href": "https://jupyter.org/", "label": "Jupyter Notebook", "type": "a" }, { "href": "https://www.kaggle.com/docs/notebooks", "label": "Kaggle Notebooks", "type": "a" }, { "href": "https://gradient.run/notebooks", "label": "Paperspace Gradient", "type": "a" }, { "href": "https://console.paperspace.com/signup?R=lg6rnx", "label": "this link", "type": "a" }, { "href": "https://forums.fast.ai/c/p1v5/54", "label": "wonderful online community", "type": "a" } ], "repair_version": 2, "repaired_at": "2026-10-14T10:53:42Z", "source_url": "https://course.fast.ai", "papers": [ { "status": "ok", "url": "http://www.ieomsociety.org/ieom2020/papers/37.pdf", "bytes": 1143132, "reused": false, "local_path": "papers/repair/8eb07589750c842746fb.pdf" } ], "actual_video_files": [], "body_chars": 12786, "expected_body_images": 5, "discovery_status": "ok", "delivery_status": "ok", "missing_reason": "", "raw_html": "attachments/4f7dd672289b/pages/source.html", "local_html": "attachments/4f7dd672289b/pages/article.html", "body_base_path": "attachments/4f7dd672289b/pages/", "body_markdown_path": "attachments/4f7dd672289b/pages/article.md" }