{"id":28640877,"url":"https://github.com/jackfrued/deep-learning-is-nothing","last_synced_at":"2026-01-31T03:32:21.532Z","repository":{"id":273710875,"uuid":"920532345","full_name":"jackfrued/Deep-Learning-Is-Nothing","owner":"jackfrued","description":"深度学习就是大力出奇迹","archived":false,"fork":false,"pushed_at":"2025-01-22T14:06:03.000Z","size":3,"stargazers_count":26,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-12T20:37:22.631Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jackfrued.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-22T10:15:23.000Z","updated_at":"2025-06-09T13:27:10.000Z","dependencies_parsed_at":"2025-01-22T14:45:34.298Z","dependency_job_id":null,"html_url":"https://github.com/jackfrued/Deep-Learning-Is-Nothing","commit_stats":null,"previous_names":["jackfrued/deep-learning-is-nothing"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jackfrued/Deep-Learning-Is-Nothing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackfrued%2FDeep-Learning-Is-Nothing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackfrued%2FDeep-Learning-Is-Nothing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackfrued%2FDeep-Learning-Is-Nothing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackfrued%2FDeep-Learning-Is-Nothing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jackfrued","download_url":"https://codeload.github.com/jackfrued/Deep-Learning-Is-Nothing/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackfrued%2FDeep-Learning-Is-Nothing/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28928148,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-31T02:59:34.861Z","status":"ssl_error","status_checked_at":"2026-01-31T02:59:05.369Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-06-12T20:36:19.575Z","updated_at":"2026-01-31T03:32:21.516Z","avatar_url":"https://github.com/jackfrued.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep-Learning-Is-Nothing\n深度学习没什么了不起，也不过就是大力出奇迹。弄一个 30 天的学习计划，拿捏！！！\n\n### **第1天：深度学习概述与PyTorch基础**\n\n- **目标：** 了解深度学习基础，熟悉PyTorch基础操作。\n- **任务：**\n    - 深度学习概述：什么是深度学习，神经网络的基本原理。\n    - PyTorch介绍：张量（Tensor）及基本操作。\n    - 搭建一个简单的神经网络模型。\n- **学习资源：**\n    - 《Deep Learning with Python》第1章\n    - PyTorch官方文档：[Tensors](https://pytorch.org/tutorials/beginner/basics/tensorqs_tutorial.html)\n\n------\n\n### **第2天：PyTorch中的自动微分与模型搭建**\n\n- **目标：** 掌握PyTorch的自动求导功能，构建第一个神经网络。\n- **任务：**\n    - 学习PyTorch的自动求导（autograd）。\n    - 搭建一个简单的神经网络，学习模型定义和训练流程。\n- **学习资源：**\n    - PyTorch官方文档：[Automatic Differentiation with `torch.autograd`](https://pytorch.org/tutorials/beginner/basics/autogradqs_tutorial.html)\n\n------\n\n### **第3天：前馈神经网络（Feedforward Neural Networks）**\n\n- **目标：** 深入了解前馈神经网络架构。\n- **任务：**\n    - 理解前馈神经网络的组成：输入层、隐藏层和输出层。\n    - 实现一个简单的前馈神经网络用于分类任务。\n- **学习资源：**\n    - 《Deep Learning with Python》第2章\n\n------\n\n### **第4天：损失函数与优化算法**\n\n- **目标：** 理解深度学习中的损失函数和优化算法。\n- **任务：**\n    - 了解常用的损失函数（如交叉熵损失、均方误差）。\n    - 了解优化算法（SGD, Adam）以及如何在PyTorch中使用它们。\n- **学习资源：**\n    - 《Deep Learning with Python》 第3章\n\n------\n\n### **第5天：训练神经网络与调参**\n\n- **目标：** 学习如何训练神经网络并调节超参数。\n- **任务：**\n    - 训练一个神经网络进行分类任务。\n    - 学习如何调节学习率、批次大小等超参数。\n- **学习资源：**\n    - 《Deep Learning with Python》 第4章\n\n------\n\n### **第6-10天：卷积神经网络（CNN）基础**\n\n- **目标：** 学习卷积神经网络的基本构建块：卷积层、池化层。\n- **任务：**\n    - 理解卷积神经网络的工作原理：卷积操作、池化操作。\n    - 使用CNN进行图像分类任务。\n- **学习资源：**\n    - 《Deep Learning with Python》 第5章\n\n------\n\n### **第11天：深入卷积神经网络（CNN）**\n\n- **目标：** 理解更深层次的卷积网络架构。\n- **任务：**\n    - 学习VGG、ResNet、Inception等网络架构。\n    - 了解如何应用这些网络架构。\n- **学习资源：**\n    - 《Deep Learning with Python》第6章\n\n------\n\n### **第12-14天：卷积神经网络应用**\n\n- **目标：** 使用预训练模型进行迁移学习。\n- **任务：**\n    - 使用PyTorch加载预训练模型（如ResNet、VGG）并进行微调。\n    - 使用微调模型进行图像分类。\n- **学习资源：**\n    - 《Deep Learning with Python》第7章\n\n------\n\n### **第15-16天：循环神经网络（RNN）与自然语言处理（NLP）**\n\n- **目标：** 了解RNN的基本原理及其在NLP中的应用。\n- **任务：**\n    - 学习RNN、LSTM、GRU的工作原理。\n    - 使用RNN进行情感分析任务。\n- **学习资源：**\n    - 《Deep Learning with Python》 第8章\n\n------\n\n### **第17-18天：自然语言处理任务（NLP）**\n\n- **目标：** 学习文本分类、序列标注等NLP任务。\n- **任务：**\n    - 使用LSTM进行情感分析、文本分类。\n    - 学习如何处理文本数据，进行词嵌入和模型训练。\n- **学习资源：**\n    - 《Deep Learning with Python》第9章\n\n------\n\n### **第19-21天：Transformer模型与Attention机制**\n\n- **目标：** 学习Transformer模型及其Attention机制。\n- **任务：**\n    - 理解Transformer模型的核心思想。\n    - 学习Attention机制的作用及应用。\n- **学习资源：**\n    - [Attention Is All You Need](https://arxiv.org/pdf/1706.03762)\n    - [Hugging Face教程](https://huggingface.co/docs/transformers/index)\n\n------\n\n### **第22-25天：BERT与GPT模型**\n\n- **目标：** 了解BERT和GPT模型，并学会如何使用它们。\n- **任务：**\n    - 理解BERT和GPT的架构及其在NLP中的应用。\n    - 使用预训练的BERT进行文本分类任务。\n- **学习资源：**\n    - Hugging Face教程\n    - [GPT模型介绍与实现](https://github.com/openai/gpt-3)\n\n------\n\n### **第26-30天：综合项目与实践**\n\n- **目标：** 完成一个深度学习项目，结合CNN和NLP技术。\n- 任务：\n    - 选择一个项目（如图像分类+文本处理），整合所学的知识。\n    - 进行模型训练、评估与优化。\n- 学习资源：\n    - [Kaggle竞赛](https://www.kaggle.com/)\n    - PyTorch官方教程\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjackfrued%2Fdeep-learning-is-nothing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjackfrued%2Fdeep-learning-is-nothing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjackfrued%2Fdeep-learning-is-nothing/lists"}