flykhan
2536c937e3
翻译自英文原版 maths-cs-ai-compendium，共 20 章全部完成。 第01章 向量 | 第02章 矩阵 | 第03章 微积分 第04章 统计学 | 第05章 概率论 | 第06章 机器学习 第07章 计算语言学 | 第08章 计算机视觉 | 第09章 音频与语音 第10章 多模态学习 | 第11章 自主系统 | 第12章 图神经网络 第13章 计算与操作系统 | 第14章 数据结构与算法 第15章 生产级软件工程 | 第16章 SIMD与GPU编程 第17章 AI推理 | 第18章 ML系统设计 第19章 应用人工智能 | 第20章 前沿人工智能 翻译说明： - 所有数学公式 $...$ / $$...$$、代码块、图片引用完整保留 - mkdocs.yml 配置中文导航 + language: zh - README.md 已翻译为中文（兼 docs/index.md） - docs/ 目录包含指向各章文件的 symlink - 约 29,000 行中文内容，排除 .cache/ 构建缓存
97 lines
6.4 KiB
XML
97 lines
6.4 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 700 280" width="700" height="280">
|
|
<defs>
|
|
<marker id="zs-blue" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6 Z" fill="#3498db"/>
|
|
</marker>
|
|
<marker id="zs-red" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6 Z" fill="#e74c3c"/>
|
|
</marker>
|
|
<marker id="zs-gray" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6 Z" fill="#666"/>
|
|
</marker>
|
|
<marker id="zs-green" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6 Z" fill="#27ae60"/>
|
|
</marker>
|
|
</defs>
|
|
|
|
<!-- Title -->
|
|
<text x="350" y="22" text-anchor="middle" font-family="Arial, sans-serif" font-size="14" font-weight="bold" fill="#333">Zero-Shot Classification with CLIP</text>
|
|
|
|
<!-- Image input -->
|
|
<rect x="20" y="100" width="70" height="60" rx="8" fill="#f39c12" fill-opacity="0.15" stroke="#f39c12" stroke-width="1.5"/>
|
|
<text x="55" y="128" text-anchor="middle" font-family="Arial, sans-serif" font-size="16" fill="#f39c12">🐕</text>
|
|
<text x="55" y="148" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">Image</text>
|
|
|
|
<!-- Image Encoder -->
|
|
<rect x="118" y="100" width="95" height="60" rx="8" fill="#3498db" fill-opacity="0.12" stroke="#3498db" stroke-width="1.5"/>
|
|
<text x="165" y="128" text-anchor="middle" font-family="Arial, sans-serif" font-size="10" font-weight="bold" fill="#3498db">Image</text>
|
|
<text x="165" y="143" text-anchor="middle" font-family="Arial, sans-serif" font-size="10" font-weight="bold" fill="#3498db">Encoder</text>
|
|
|
|
<!-- Arrow image to encoder -->
|
|
<line x1="90" y1="130" x2="110" y2="130" stroke="#3498db" stroke-width="1.5" marker-end="url(#zs-blue)"/>
|
|
|
|
<!-- Image embedding vector -->
|
|
<line x1="213" y1="130" x2="260" y2="130" stroke="#3498db" stroke-width="1.5" marker-end="url(#zs-blue)"/>
|
|
<text x="237" y="124" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#3498db">embed</text>
|
|
|
|
<!-- Text prompts -->
|
|
<rect x="118" y="42" width="148" height="24" rx="6" fill="#e74c3c" fill-opacity="0.08" stroke="#e74c3c" stroke-width="1"/>
|
|
<text x="192" y="58" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#e74c3c">"a photo of a dog"</text>
|
|
|
|
<rect x="118" y="188" width="148" height="24" rx="6" fill="#e74c3c" fill-opacity="0.08" stroke="#e74c3c" stroke-width="1"/>
|
|
<text x="192" y="204" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#e74c3c">"a photo of a cat"</text>
|
|
|
|
<rect x="118" y="230" width="148" height="24" rx="6" fill="#e74c3c" fill-opacity="0.08" stroke="#e74c3c" stroke-width="1"/>
|
|
<text x="192" y="246" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#e74c3c">"a photo of a car"</text>
|
|
|
|
<!-- Text Encoder box -->
|
|
<rect x="295" y="42" width="80" height="24" rx="6" fill="#e74c3c" fill-opacity="0.12" stroke="#e74c3c" stroke-width="1.5"/>
|
|
<text x="335" y="58" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" font-weight="bold" fill="#e74c3c">Text Enc.</text>
|
|
|
|
<rect x="295" y="188" width="80" height="24" rx="6" fill="#e74c3c" fill-opacity="0.12" stroke="#e74c3c" stroke-width="1.5"/>
|
|
<text x="335" y="204" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" font-weight="bold" fill="#e74c3c">Text Enc.</text>
|
|
|
|
<rect x="295" y="230" width="80" height="24" rx="6" fill="#e74c3c" fill-opacity="0.12" stroke="#e74c3c" stroke-width="1.5"/>
|
|
<text x="335" y="246" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" font-weight="bold" fill="#e74c3c">Text Enc.</text>
|
|
|
|
<!-- Arrows from prompts to text encoders -->
|
|
<line x1="266" y1="54" x2="288" y2="54" stroke="#e74c3c" stroke-width="1" marker-end="url(#zs-red)"/>
|
|
<line x1="266" y1="200" x2="288" y2="200" stroke="#e74c3c" stroke-width="1" marker-end="url(#zs-red)"/>
|
|
<line x1="266" y1="242" x2="288" y2="242" stroke="#e74c3c" stroke-width="1" marker-end="url(#zs-red)"/>
|
|
|
|
<!-- Cosine similarity block -->
|
|
<rect x="410" y="38" width="110" height="224" rx="8" fill="#f8f8f8" stroke="#ccc" stroke-width="1"/>
|
|
<text x="465" y="56" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" font-weight="bold" fill="#666">Cosine Sim.</text>
|
|
|
|
<!-- Arrows from text encoders to cosine sim -->
|
|
<line x1="375" y1="54" x2="403" y2="54" stroke="#666" stroke-width="1" marker-end="url(#zs-gray)"/>
|
|
<line x1="375" y1="200" x2="403" y2="200" stroke="#666" stroke-width="1" marker-end="url(#zs-gray)"/>
|
|
<line x1="375" y1="242" x2="403" y2="242" stroke="#666" stroke-width="1" marker-end="url(#zs-gray)"/>
|
|
|
|
<!-- Arrow from image embedding to cosine sim -->
|
|
<line x1="268" y1="130" x2="403" y2="130" stroke="#3498db" stroke-width="1.5" stroke-dasharray="5,3"/>
|
|
|
|
<!-- Similarity bars -->
|
|
<!-- Dog — highest (green) -->
|
|
<text x="428" y="90" font-family="Arial, sans-serif" font-size="9" fill="#333">dog</text>
|
|
<rect x="450" y="78" width="55" height="16" rx="4" fill="#27ae60" fill-opacity="0.7"/>
|
|
<text x="510" y="90" text-anchor="start" font-family="Arial, sans-serif" font-size="9" font-weight="bold" fill="#27ae60">0.92</text>
|
|
|
|
<!-- Cat — medium (gray) -->
|
|
<text x="428" y="144" font-family="Arial, sans-serif" font-size="9" fill="#333">cat</text>
|
|
<rect x="450" y="132" width="22" height="16" rx="4" fill="#999" fill-opacity="0.4"/>
|
|
<text x="478" y="144" text-anchor="start" font-family="Arial, sans-serif" font-size="9" fill="#999">0.35</text>
|
|
|
|
<!-- Car — low (gray) -->
|
|
<text x="428" y="208" font-family="Arial, sans-serif" font-size="9" fill="#333">car</text>
|
|
<rect x="450" y="196" width="10" height="16" rx="4" fill="#999" fill-opacity="0.3"/>
|
|
<text x="466" y="208" text-anchor="start" font-family="Arial, sans-serif" font-size="9" fill="#999">0.08</text>
|
|
|
|
<!-- Prediction arrow -->
|
|
<line x1="540" y1="86" x2="575" y2="86" stroke="#27ae60" stroke-width="1.5" marker-end="url(#zs-green)"/>
|
|
|
|
<!-- Prediction label -->
|
|
<rect x="582" y="70" width="105" height="32" rx="8" fill="#27ae60" fill-opacity="0.15" stroke="#27ae60" stroke-width="1.5"/>
|
|
<text x="634" y="84" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">Predicted:</text>
|
|
<text x="634" y="97" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#27ae60">dog</text>
|
|
</svg> |