[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-156285-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-156285-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","deep-learning-for-coders-with-fastai-and-pytorch","Deep Learning for Coders - with fastai and PyTorch","","A practical guide to building, training, and deploying deep learning models using PyTorch, fastai, and Jupyter. Covers the end-to-end workflow from datasets and DataLoaders to validation, testing, and cleaning data with model-assisted inference. Explores core techniques like neural networks, optimization, loss functions, and computer-vision tasks including classification and advanced training strategies. Includes data ethics, policy considerations, and real-world production guidance. Also extends applications to collaborative filtering and tabular modeling.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/technology/","Technology",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/deep-learning-for-coders-with-fastai-and-pytorch/156285/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/deep-learning-for-coders-with-fastai-and-pytorch/156285.png","ImageObject",300,407,{"name":42,"@type":43},"Aurelia","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-15","2026-08-28",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",17,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Who is this book intended for, and what prior knowledge is assumed?","Question",{"text":63,"@type":64},"The preface outlines the target audience and what readers need to know before starting. It also explains how the learning path is structured across chapters.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the book connect model development to real production use?",{"text":68,"@type":64},"It covers the practice of deep learning from starting a project, gathering data, building DataLoaders, training, and turning a model into an online application for inference and deployment.",{"name":70,"@type":61,"acceptedAnswer":71},"What data ethics topics are addressed?",{"text":72,"@type":64},"The text includes examples and discussion of bugs and recourse, feedback loops, bias, disinformation, and how to integrate ethics into product design and implementation processes.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},156285,1787955696,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":103,"slug":104},6,50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},8,"Research & Report",30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":102,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":80,"read_time":145},1099514068365,"https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068","1. Preface  \na. Who This Book Is For  \nb. What You Need to Know  \nc. What You Will Learn  \nd. O’Reilly Online Learning  \ne. How to Contact Us  \n2. Foreword  \n3. I. Deep Learning in Practice  \n4. 1. Your Deep Learning Journey  \na. Deep Learning Is for Everyone  \nb. Neural Networks: A Brief History  \nc. Who WeAre  \nd. How to Learn Deep Learning  \ni. Your Projects and Your Mindset  \ne. The Software: PyTorch, fastai, and Jupyter (And Why It Doesn’t Matter)  \nf. Your First Model  \ni. Getting a GPU Deep Learning Server  \nii. Running Your First Notebook  \niii. What Is Machine Learning?  \niv. What Is a Neural Network?  \nv. A Bit of Deep Learning Jargon  \nvi. Limitations Inherent to Machine Learning  \nvii. How Our Image Recognizer Works  \nviii. What Our Image Recognizer Learned  \nix. Image Recognizers Can Tackle NonImage Tasks  \nx. Jargon Recap  \ng. Deep Learning Is Not Just for Image Classification  \nh. Validation Sets and Test Sets  \ni. Use Judgment in Defining Test Sets  \ni. A Choose Your Own Adventure Moment  \nj. Questionnaire  \ni. Further Research  \n5. 2. From Model to Production  \na. The Practice of Deep Learning  \ni. Starting Your Project  \nii. The State of Deep Learning  \niii. The Drivetrain Approach  \nb. Gathering Data  \nc. From Data to DataLoaders  \ni. Data Augmentation  \nd. Training Your Model, and Using It to Clean Your Data  \ne. Turning Your Model into an Online Application  \ni. Using the Model for Inference  \nii. Creating a Notebook App from the Model  \niii. Turning Your Notebook into a Real App  \niv. Deploying Your App  \nf. How to Avoid Disaster  \ni. Unforeseen Consequences and Feedback Loops  \ng. Get Writing!  \nh. Questionnaire  \ni. Further Research  \n6. 3. Data Ethics  \na. Key Examples for Data Ethics  \ni. Bugs and Recourse: Buggy Algorithm Used for Healthcare Benefits  \nii. Feedback Loops: YouTube’s Recommendation System  \niii. Bias: Professor Latanya Sweeney“Arrested”  \niv. Why Does This Matter?  \nb. Integrating Machine Learning with Product Design  \nc. Topics in Data Ethics  \ni. Recourse and Accountability  \nii. Feedback Loops  \niii. Bias  \niv. Disinformation  \nd. Identifying and Addressing Ethical Issues  \ni. Analyze a Project You Are Working On  \nii. Processes to Implement  \niii. The Power of Diversity  \niv. Fairness, Accountability, and Transparency  \ne. Role of Policy  \ni. The Effectiveness of Regulation  \nii. Rights and Policy  \niii. Cars: A Historical Precedent  \nf. Conclusion  \ng. Questionnaire  \ni. Further Research  \nh. Deep Learning in Practice: That’s a Wrap!  \n7. II. Understanding fastai’s Applications  \n8. 4. Under the Hood: Training a Digit Classifier  \na. Pixels: The Foundations of Computer Vision  \nb. First Try: Pixel Similarity  \ni. NumPy Arrays and PyTorch Tensors  \nc. Computing Metrics Using Broadcasting  \nd. Stochastic Gradient Descent  \ni. Calculating Gradients  \nii. Stepping with a Learning Rate  \niii. An End-to-End SGD Example  \niv. Summarizing Gradient Descent  \ne. The MNIST Loss Function  \ni. Sigmoid  \nii. SGD and Mini-Batches  \nf. Putting It All Together  \ni. Creating an Optimizer  \ng. Adding a Nonlinearity  \ni. Going Deeper  \nh. Jargon Recap  \ni. Questionnaire  \ni. Further Research  \n9. 5. Image Classification  \na. From Dogs and Cats to Pet Breeds  \nb. Presizing  \ni. Checking and Debugging a DataBlock  \nc. Cross-Entropy Loss  \ni. Viewing Activations and Labels  \nii. Softmax  \niii. Log Likelihood  \niv. Taking the log  \nd. Model Interpretation  \ne. Improving Our Model  \ni. The Learning Rate Finder  \nii. Unfreezing and Transfer Learning  \niii. Discriminative Learning Rates  \niv. Selecting the Number of Epochs  \nv. Deeper Architectures  \nf. Conclusion  \ng. Questionnaire  \ni. Further Research  \n10. 6. Other Computer Vision Problems  \na. Multi-Label Classification  \ni. The Data  \nii. Constructing a DataBlock  \niii. Binary Cross Entropy  \nb. Regression  \ni. Assembling the Data  \nii. Training a Model  \nc. Conclusion  \nd. Questionnaire  \ni. Further Research  \n11. 7. Training a State-of-the-Art Model","cbCaiqEsxWnvFNk4","https://ap.wps.com/l/cbCaiqEsxWnvFNk4","pdf",11122753,1028,"English","# Preface\n## Who This Book Is For\n## What You Need to Know\n## What You Will Learn\n## How to Contact Us\n# Foreword\n# Deep Learning in Practice\n## Your Deep Learning Journey\n## From Model to Production\n## Data Ethics\n# Understanding fastai’s Applications\n## Under the Hood: Training a Digit Classifier\n## Image Classification\n## Other Computer Vision Problems\n# Training a State-of-the-Art Model\n## Collaborative Filtering Deep Dive\n## Tabular Modeling Deep Dive\n## NLP Deep Dive: RNNs","[{\"question\":\"Who is this book intended for, and what prior knowledge is assumed?\",\"answer\":\"The preface outlines the target audience and what readers need to know before starting. It also explains how the learning path is structured across chapters.\"},{\"question\":\"How does the book connect model development to real production use?\",\"answer\":\"It covers the practice of deep learning from starting a project, gathering data, building DataLoaders, training, and turning a model into an online application for inference and deployment.\"},{\"question\":\"What data ethics topics are addressed?\",\"answer\":\"The text includes examples and discussion of bugs and recourse, feedback loops, bias, disinformation, and how to integrate ethics into product design and implementation processes.\"}]","Deep Learning for Coders - with fastai and PyTorch | PDF",2591]