mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-05-06 17:21:08 -05:00
Finalize book intro and author attribution
- Updated title to match new tagline format - Added humble educational foundation section referencing CS249r course - Confirmed result-oriented 'What You'll Achieve' section works well - All branding now consistent across book and documentation - Clean author attribution without unnecessary copyright notices
This commit is contained in:
Vijay Janapa Reddi
Binary file not shown.
@@ -51,7 +51,7 @@ TinyTorch grew out of the CS249r: Tiny Machine Learning Systems course at Harvar
|
||||
|
||||
## 🎯 What You'll Build
|
||||
|
||||
### **Progressive Complexity - Each Module Builds on Previous Work**
|
||||
### **Progressive Complexity - Each Module Builds on Prior Work**
|
||||
|
||||
```{admonition} 🏗️ Foundation (Modules 0-2)
|
||||
:class: note
|
||||
@@ -121,7 +121,7 @@ model = Sequential([
|
||||
|
||||
---
|
||||
|
||||
## 📊 Proven Student Outcomes
|
||||
## 📊 Expected Student Outcomes
|
||||
|
||||
```{admonition} Real Results from Real Students
|
||||
:class: success
|
||||
@@ -142,11 +142,10 @@ model = Sequential([
|
||||
|
||||
## 🌟 What Makes This Different
|
||||
|
||||
### **🔬 Real Data, Real Systems**
|
||||
- Work with **CIFAR-10** (not toy datasets)
|
||||
- **Production-style** code organization
|
||||
- **Performance considerations** and engineering practices
|
||||
- **Professional development** workflow with automated testing
|
||||
### **🔬 Engineering Principles
|
||||
- **Production-style** code organization throughout every module
|
||||
- **Performance-focused** engineering and optimization practices
|
||||
- **Professional development** workflow with automated testing and CI
|
||||
|
||||
### **🚀 Immediate Feedback**
|
||||
- Code works **immediately** after implementation
|
||||
@@ -188,19 +187,16 @@ Traditional ML Course: TinyTorch Approach:
|
||||
├── import torch ├── class Tensor:
|
||||
├── model = nn.Linear(10, 1) │ def __add__(self, other): ...
|
||||
├── loss = nn.MSELoss() │ def backward(self): ...
|
||||
├── optimizer.step() ├── class Linear:
|
||||
└── "How does this work?" 🤷 │ def forward(self, x):
|
||||
└── optimizer.step() ├── class Linear:
|
||||
│ def forward(self, x):
|
||||
│ return x @ self.weight + self.bias
|
||||
├── def mse_loss(pred, target):
|
||||
│ return ((pred - target) ** 2).mean()
|
||||
├── class SGD:
|
||||
│ def step(self):
|
||||
│ param.data -= lr * param.grad
|
||||
└── "I implemented every line!" 💪
|
||||
└── param.data -= lr * param.grad
|
||||
|
||||
Transform your curiosity "How does this work?" 🤷 into confidence: "I built every part myself!" 💪
|
||||
```
|
||||
|
||||
**Result:** You become the person others come to when they need to understand "how PyTorch actually works under the hood."
|
||||
|
||||
---
|
||||
|
||||
*Built with ❤️ for hands-on ML systems education. Every line of code you write brings you closer to understanding how modern AI actually works.*
|
||||
**Result:** You become the person others come to when they need to understand "how PyTorch actually works under the hood." Every line of code you write brings you closer to understanding how modern AI works.
|
||||
|
||||
@@ -426,16 +426,16 @@ document.write(`
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#educational-foundation">📚 Educational Foundation</a></li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#choose-your-learning-path">🚀 Choose Your Learning Path</a></li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#what-you-ll-build">🎯 What You’ll Build</a><ul class="nav section-nav flex-column">
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#progressive-complexity-each-module-builds-on-previous-work"><strong>Progressive Complexity - Each Module Builds on Previous Work</strong></a></li>
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#progressive-complexity-each-module-builds-on-prior-work"><strong>Progressive Complexity - Each Module Builds on Prior Work</strong></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#learning-philosophy-build-use-understand">🎓 Learning Philosophy: Build → Use → Understand</a><ul class="nav section-nav flex-column">
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#example-how-you-ll-learn-activation-functions"><strong>Example: How You’ll Learn Activation Functions</strong></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#proven-student-outcomes">📊 Proven Student Outcomes</a></li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#expected-student-outcomes">📊 Expected Student Outcomes</a></li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#what-makes-this-different">🌟 What Makes This Different</a><ul class="nav section-nav flex-column">
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#real-data-real-systems"><strong>🔬 Real Data, Real Systems</strong></a></li>
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#engineering-principles">**🔬 Engineering Principles</a></li>
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#immediate-feedback"><strong>🚀 Immediate Feedback</strong></a></li>
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#progressive-complexity"><strong>🎯 Progressive Complexity</strong></a></li>
|
||||
</ul>
|
||||
@@ -508,8 +508,8 @@ document.write(`
|
||||
<hr class="docutils" />
|
||||
<section id="what-you-ll-build">
|
||||
<h2>🎯 What You’ll Build<a class="headerlink" href="#what-you-ll-build" title="Link to this heading">#</a></h2>
|
||||
<section id="progressive-complexity-each-module-builds-on-previous-work">
|
||||
<h3><strong>Progressive Complexity - Each Module Builds on Previous Work</strong><a class="headerlink" href="#progressive-complexity-each-module-builds-on-previous-work" title="Link to this heading">#</a></h3>
|
||||
<section id="progressive-complexity-each-module-builds-on-prior-work">
|
||||
<h3><strong>Progressive Complexity - Each Module Builds on Prior Work</strong><a class="headerlink" href="#progressive-complexity-each-module-builds-on-prior-work" title="Link to this heading">#</a></h3>
|
||||
<div class="note admonition">
|
||||
<p class="admonition-title">🏗️ Foundation (Modules 0-2)</p>
|
||||
<p><strong>Week 1-3: Core Infrastructure</strong></p>
|
||||
@@ -580,8 +580,8 @@ document.write(`
|
||||
</section>
|
||||
</section>
|
||||
<hr class="docutils" />
|
||||
<section id="proven-student-outcomes">
|
||||
<h2>📊 Proven Student Outcomes<a class="headerlink" href="#proven-student-outcomes" title="Link to this heading">#</a></h2>
|
||||
<section id="expected-student-outcomes">
|
||||
<h2>📊 Expected Student Outcomes<a class="headerlink" href="#expected-student-outcomes" title="Link to this heading">#</a></h2>
|
||||
<div class="success admonition">
|
||||
<p class="admonition-title">Real Results from Real Students</p>
|
||||
<p><strong>After completing TinyTorch, students consistently:</strong></p>
|
||||
@@ -597,13 +597,12 @@ document.write(`
|
||||
<hr class="docutils" />
|
||||
<section id="what-makes-this-different">
|
||||
<h2>🌟 What Makes This Different<a class="headerlink" href="#what-makes-this-different" title="Link to this heading">#</a></h2>
|
||||
<section id="real-data-real-systems">
|
||||
<h3><strong>🔬 Real Data, Real Systems</strong><a class="headerlink" href="#real-data-real-systems" title="Link to this heading">#</a></h3>
|
||||
<section id="engineering-principles">
|
||||
<h3>**🔬 Engineering Principles<a class="headerlink" href="#engineering-principles" title="Link to this heading">#</a></h3>
|
||||
<ul class="simple">
|
||||
<li><p>Work with <strong>CIFAR-10</strong> (not toy datasets)</p></li>
|
||||
<li><p><strong>Production-style</strong> code organization</p></li>
|
||||
<li><p><strong>Performance considerations</strong> and engineering practices</p></li>
|
||||
<li><p><strong>Professional development</strong> workflow with automated testing</p></li>
|
||||
<li><p><strong>Production-style</strong> code organization throughout every module</p></li>
|
||||
<li><p><strong>Performance-focused</strong> engineering and optimization practices</p></li>
|
||||
<li><p><strong>Professional development</strong> workflow with automated testing and CI</p></li>
|
||||
</ul>
|
||||
</section>
|
||||
<section id="immediate-feedback">
|
||||
@@ -647,20 +646,19 @@ document.write(`
|
||||
<span class="err">├──</span> <span class="kn">import</span><span class="w"> </span><span class="nn">torch</span> <span class="err">├──</span> <span class="k">class</span><span class="w"> </span><span class="nc">Tensor</span><span class="p">:</span>
|
||||
<span class="err">├──</span> <span class="n">model</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> <span class="err">│</span> <span class="k">def</span><span class="w"> </span><span class="fm">__add__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">):</span> <span class="o">...</span>
|
||||
<span class="err">├──</span> <span class="n">loss</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MSELoss</span><span class="p">()</span> <span class="err">│</span> <span class="k">def</span><span class="w"> </span><span class="nf">backward</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> <span class="o">...</span>
|
||||
<span class="err">├──</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">step</span><span class="p">()</span> <span class="err">├──</span> <span class="k">class</span><span class="w"> </span><span class="nc">Linear</span><span class="p">:</span>
|
||||
<span class="err">└──</span> <span class="s2">"How does this work?"</span> <span class="err">🤷</span> <span class="err">│</span> <span class="k">def</span><span class="w"> </span><span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
|
||||
<span class="err">└──</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">step</span><span class="p">()</span> <span class="err">├──</span> <span class="k">class</span><span class="w"> </span><span class="nc">Linear</span><span class="p">:</span>
|
||||
<span class="err">│</span> <span class="k">def</span><span class="w"> </span><span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
|
||||
<span class="err">│</span> <span class="k">return</span> <span class="n">x</span> <span class="o">@</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">bias</span>
|
||||
<span class="err">├──</span> <span class="k">def</span><span class="w"> </span><span class="nf">mse_loss</span><span class="p">(</span><span class="n">pred</span><span class="p">,</span> <span class="n">target</span><span class="p">):</span>
|
||||
<span class="err">│</span> <span class="k">return</span> <span class="p">((</span><span class="n">pred</span> <span class="o">-</span> <span class="n">target</span><span class="p">)</span> <span class="o">**</span> <span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
|
||||
<span class="err">├──</span> <span class="k">class</span><span class="w"> </span><span class="nc">SGD</span><span class="p">:</span>
|
||||
<span class="err">│</span> <span class="k">def</span><span class="w"> </span><span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="err">│</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span> <span class="o">-=</span> <span class="n">lr</span> <span class="o">*</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span>
|
||||
<span class="err">└──</span> <span class="s2">"I implemented every line!"</span> <span class="err">💪</span>
|
||||
<span class="err">└──</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span> <span class="o">-=</span> <span class="n">lr</span> <span class="o">*</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span>
|
||||
|
||||
<span class="n">Transform</span> <span class="n">your</span> <span class="n">curiosity</span> <span class="s2">"How does this work?"</span> <span class="err">🤷</span> <span class="n">into</span> <span class="n">confidence</span><span class="p">:</span> <span class="s2">"I built every part myself!"</span> <span class="err">💪</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p><strong>Result:</strong> You become the person others come to when they need to understand “how PyTorch actually works under the hood.”</p>
|
||||
<hr class="docutils" />
|
||||
<p><em>Built with ❤️ for hands-on ML systems education. Every line of code you write brings you closer to understanding how modern AI actually works.</em></p>
|
||||
<p><strong>Result:</strong> You become the person others come to when they need to understand “how PyTorch actually works under the hood.” Every line of code you write brings you closer to understanding how modern AI works.</p>
|
||||
</section>
|
||||
<div class="toctree-wrapper compound">
|
||||
</div>
|
||||
@@ -734,16 +732,16 @@ document.write(`
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#educational-foundation">📚 Educational Foundation</a></li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#choose-your-learning-path">🚀 Choose Your Learning Path</a></li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#what-you-ll-build">🎯 What You’ll Build</a><ul class="nav section-nav flex-column">
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#progressive-complexity-each-module-builds-on-previous-work"><strong>Progressive Complexity - Each Module Builds on Previous Work</strong></a></li>
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#progressive-complexity-each-module-builds-on-prior-work"><strong>Progressive Complexity - Each Module Builds on Prior Work</strong></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#learning-philosophy-build-use-understand">🎓 Learning Philosophy: Build → Use → Understand</a><ul class="nav section-nav flex-column">
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#example-how-you-ll-learn-activation-functions"><strong>Example: How You’ll Learn Activation Functions</strong></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#proven-student-outcomes">📊 Proven Student Outcomes</a></li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#expected-student-outcomes">📊 Expected Student Outcomes</a></li>
|
||||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#what-makes-this-different">🌟 What Makes This Different</a><ul class="nav section-nav flex-column">
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#real-data-real-systems"><strong>🔬 Real Data, Real Systems</strong></a></li>
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#engineering-principles">**🔬 Engineering Principles</a></li>
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#immediate-feedback"><strong>🚀 Immediate Feedback</strong></a></li>
|
||||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#progressive-complexity"><strong>🎯 Progressive Complexity</strong></a></li>
|
||||
</ul>
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -51,7 +51,7 @@ TinyTorch grew out of the CS249r: Tiny Machine Learning Systems course at Harvar
|
||||
|
||||
## 🎯 What You'll Build
|
||||
|
||||
### **Progressive Complexity - Each Module Builds on Previous Work**
|
||||
### **Progressive Complexity - Each Module Builds on Prior Work**
|
||||
|
||||
```{admonition} 🏗️ Foundation (Modules 0-2)
|
||||
:class: note
|
||||
@@ -121,7 +121,7 @@ model = Sequential([
|
||||
|
||||
---
|
||||
|
||||
## 📊 Proven Student Outcomes
|
||||
## 📊 Expected Student Outcomes
|
||||
|
||||
```{admonition} Real Results from Real Students
|
||||
:class: success
|
||||
@@ -142,11 +142,10 @@ model = Sequential([
|
||||
|
||||
## 🌟 What Makes This Different
|
||||
|
||||
### **🔬 Real Data, Real Systems**
|
||||
- Work with **CIFAR-10** (not toy datasets)
|
||||
- **Production-style** code organization
|
||||
- **Performance considerations** and engineering practices
|
||||
- **Professional development** workflow with automated testing
|
||||
### **🔬 Engineering Principles**
|
||||
- **Production-style** code organization throughout every module
|
||||
- **Performance-focused** engineering and optimization practices
|
||||
- **Professional development** workflow with automated testing and CI
|
||||
|
||||
### **🚀 Immediate Feedback**
|
||||
- Code works **immediately** after implementation
|
||||
@@ -188,19 +187,16 @@ Traditional ML Course: TinyTorch Approach:
|
||||
├── import torch ├── class Tensor:
|
||||
├── model = nn.Linear(10, 1) │ def __add__(self, other): ...
|
||||
├── loss = nn.MSELoss() │ def backward(self): ...
|
||||
├── optimizer.step() ├── class Linear:
|
||||
└── "How does this work?" 🤷 │ def forward(self, x):
|
||||
└── optimizer.step() ├── class Linear:
|
||||
│ def forward(self, x):
|
||||
│ return x @ self.weight + self.bias
|
||||
├── def mse_loss(pred, target):
|
||||
│ return ((pred - target) ** 2).mean()
|
||||
├── class SGD:
|
||||
│ def step(self):
|
||||
│ param.data -= lr * param.grad
|
||||
└── "I implemented every line!" 💪
|
||||
└── param.data -= lr * param.grad
|
||||
|
||||
Go from "How does this work?" 🤷 to "I implemented every line!" 💪
|
||||
```
|
||||
|
||||
**Result:** You become the person others come to when they need to understand "how PyTorch actually works under the hood."
|
||||
|
||||
---
|
||||
|
||||
*Built with ❤️ for hands-on ML systems education. Every line of code you write brings you closer to understanding how modern AI actually works.*
|
||||
**Result:** You become the person others come to when they need to understand "how PyTorch actually works under the hood." Every line of code you write brings you closer to understanding how modern AI works.
|
||||
|
||||
Reference in New Issue
Block a user