Skip to content

Commit

Permalink
Update course book
Browse files Browse the repository at this point in the history
  • Loading branch information
actions-user committed Nov 15, 2024
1 parent 4efeae6 commit 647151e
Show file tree
Hide file tree
Showing 151 changed files with 1,673 additions and 1,669 deletions.
2 changes: 1 addition & 1 deletion .buildinfo
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
config: 665b87bc356bcf7d6c6e949e546d49c8
config: 1060e10d9f90f986cce81c57e41aa119
tags: 645f666f9bcd5a90fca523b33c5a78b7
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
40 changes: 17 additions & 23 deletions _sources/tutorials/Schedule/daily_schedules.md
Original file line number Diff line number Diff line change
@@ -1,39 +1,33 @@
# General schedule

## 2024 course will run: July 8 - 26, 2024

Course live events: TBD — will update
## 2025 course will run: July 7 - 25, 2025

## Course overview

* Sun, July 7: Opening Ceremonies
* 8:30 am UTC
* 5:30 pm UTC

* Week 1
* Mon, July 8: Basics and Pytorch
* Tue, July 9: Linear Deep Learning
* Wed, July 10: Multilayer Perceptrons
* Thu, July 11: Projects day
* Fri, July 12: Optimization
* Mon, July 7: Basics and Pytorch
* Tue, July 8: Linear Deep Learning
* Wed, July 9: Multilayer Perceptrons
* Thu, July 10: Projects day
* Fri, July 11: Optimization

* Week 2
* Mon, July 15: Regularization
* Tue, July 16: Convnets and DL Thinking 1
* Wed, July 17: Modern Convnets
* Thu, July 18: Generative models (VAEs and Diffusion models)
* Fri, July 19: Attention and Transformers
* Mon, July 14: Regularization
* Tue, July 15: Convnets and DL Thinking 1
* Wed, July 16: Modern Convnets
* Thu, July 17: Generative models (VAEs and Diffusion models)
* Fri, July 18: Attention and Transformers

* Week 3: Advanced concepts
* Mon, July 22: Time Series and Natural Language Processing
* Tue, July 23: DL Thinking 2 & Half Projects Day (Abstract Writing)
* Wed, July 24: Unsupervised and Self-supervised learning
* Thu, July 25: Basic Reinforcement Learning
* Fri, July 26: Reinforcement Learning for Games & DL Thinking 3
* Mon, July 21: Time Series and Natural Language Processing
* Tue, July 22: DL Thinking 2 & Half Projects Day (Abstract Writing)
* Wed, July 23: Unsupervised and Self-supervised learning
* Thu, July 24: Basic Reinforcement Learning
* Fri, July 25: Reinforcement Learning for Games & DL Thinking 3
----

## Daily coursework schedule
These schedules refer to the coursework time.
### 2025 course schedule coming soon. Below is the 2024 course schedule.

### General schedule
All days (except W1D4, W3D2, and W3D5) will follow this schedule for course time:
Expand Down
4 changes: 2 additions & 2 deletions projects/ComputerVision/data_augmentation.html
Original file line number Diff line number Diff line change
Expand Up @@ -1763,8 +1763,8 @@ <h2>Cutout<a class="headerlink" href="#cutout" title="Permalink to this heading"
<section id="mixup">
<h2>Mixup<a class="headerlink" href="#mixup" title="Permalink to this heading">#</a></h2>
<p>Mixup is a data augmentation technique that combines pairs of examples via a convex combination of the images and the labels. Given images <span class="math notranslate nohighlight">\(x_i\)</span> and <span class="math notranslate nohighlight">\(x_j\)</span> with labels <span class="math notranslate nohighlight">\(y_i\)</span> and <span class="math notranslate nohighlight">\(y_j\)</span>, respectively, and <span class="math notranslate nohighlight">\(\lambda \in [0, 1]\)</span>, mixup creates a new image <span class="math notranslate nohighlight">\(\hat{x}\)</span> with label <span class="math notranslate nohighlight">\(\hat{y}\)</span> the following way:</p>
<div class="amsmath math notranslate nohighlight" id="equation-efffedd2-3c0f-454f-b100-a54d6e702ebe">
<span class="eqno">(128)<a class="headerlink" href="#equation-efffedd2-3c0f-454f-b100-a54d6e702ebe" title="Permalink to this equation">#</a></span>\[\begin{align}
<div class="amsmath math notranslate nohighlight" id="equation-2ad93d08-692c-42e1-893e-5fbbbdc17a6d">
<span class="eqno">(128)<a class="headerlink" href="#equation-2ad93d08-692c-42e1-893e-5fbbbdc17a6d" title="Permalink to this equation">#</a></span>\[\begin{align}
\hat{x} &amp;= \lambda x_i + (1 - \lambda) x_j \\
\hat{y} &amp;= \lambda y_i + (1 - \lambda) y_j
\end{align}\]</div>
Expand Down
64 changes: 32 additions & 32 deletions projects/modelingsteps/Example_Deep_Learning_Project.html
Original file line number Diff line number Diff line change
Expand Up @@ -2067,33 +2067,33 @@ <h2>Build model<a class="headerlink" href="#build-model" title="Permalink to thi
</div>
</div>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [100/500], Step [1/2], Loss: 1.1024, Accuracy: 62.98%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [100/500], Step [1/2], Loss: 0.9360, Accuracy: 67.83%
------------------------------------------
Epoch [100/500], Step [2/2], Loss: 1.1382, Accuracy: 62.60%
Epoch [100/500], Step [2/2], Loss: 1.0686, Accuracy: 61.82%
------------------------------------------
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [200/500], Step [1/2], Loss: 0.8495, Accuracy: 68.99%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [200/500], Step [1/2], Loss: 0.6698, Accuracy: 77.13%
------------------------------------------
Epoch [200/500], Step [2/2], Loss: 0.8329, Accuracy: 69.19%
Epoch [200/500], Step [2/2], Loss: 0.6251, Accuracy: 77.33%
------------------------------------------
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [300/500], Step [1/2], Loss: 0.7093, Accuracy: 75.58%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [300/500], Step [1/2], Loss: 0.5240, Accuracy: 82.36%
------------------------------------------
Epoch [300/500], Step [2/2], Loss: 0.6627, Accuracy: 75.58%
Epoch [300/500], Step [2/2], Loss: 0.4623, Accuracy: 81.98%
------------------------------------------
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [400/500], Step [1/2], Loss: 0.5297, Accuracy: 79.65%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [400/500], Step [1/2], Loss: 0.3841, Accuracy: 85.27%
------------------------------------------
Epoch [400/500], Step [2/2], Loss: 0.5616, Accuracy: 80.04%
Epoch [400/500], Step [2/2], Loss: 0.4109, Accuracy: 86.82%
------------------------------------------
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [500/500], Step [1/2], Loss: 0.4855, Accuracy: 83.72%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [500/500], Step [1/2], Loss: 0.3158, Accuracy: 88.18%
------------------------------------------
Epoch [500/500], Step [2/2], Loss: 0.4633, Accuracy: 85.66%
Epoch [500/500], Step [2/2], Loss: 0.3384, Accuracy: 88.95%
------------------------------------------
</pre></div>
</div>
Expand Down Expand Up @@ -2123,7 +2123,7 @@ <h2>Build model<a class="headerlink" href="#build-model" title="Permalink to thi
</div>
</div>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Test Accuracy of the model on the 172 test moves: 76.744%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Test Accuracy of the model on the 172 test moves: 87.209%
</pre></div>
</div>
</div>
Expand All @@ -2137,7 +2137,7 @@ <h2>Build model<a class="headerlink" href="#build-model" title="Permalink to thi
</div>
</div>
<div class="cell_output docutils container">
<img alt="../../_images/9296fda502703a92010d8097ac19f5979fdfaf1ca2e3ca86f95f31ffb27458af.png" src="../../_images/9296fda502703a92010d8097ac19f5979fdfaf1ca2e3ca86f95f31ffb27458af.png" />
<img alt="../../_images/409f9fd79de9fd07bc781a10009f52d974e309f50a7998389a24e3d09c2b3df0.png" src="../../_images/409f9fd79de9fd07bc781a10009f52d974e309f50a7998389a24e3d09c2b3df0.png" />
</div>
</div>
<p>The errors vary each time the model is run, but a common error seems to be that head scratching is predicted from some other movements that also involve arms a lot: throw/catch, hand clapping, phone talking, checking watch, hand waving, taking photo. If we train the model longer, these errors tend to go away as well. For some reason, crossed legged sitting is sometimes misclassified for crawling, but this doesn’t always happen.</p>
Expand Down Expand Up @@ -2225,10 +2225,10 @@ <h1>Step 8: Modeling completion<a class="headerlink" href="#step-8-modeling-comp
</div>
</div>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>73.25581395348837
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>73.83720930232558
</pre></div>
</div>
<img alt="../../_images/ef5c82744f505d4b0f20340789cb1b66af3bcbd0e92f42d5aeecb5d976c1e002.png" src="../../_images/ef5c82744f505d4b0f20340789cb1b66af3bcbd0e92f42d5aeecb5d976c1e002.png" />
<img alt="../../_images/0eb6063ba785e40e156e302d871f9a5387295004e93378f1b9c3f09fa30076a7.png" src="../../_images/0eb6063ba785e40e156e302d871f9a5387295004e93378f1b9c3f09fa30076a7.png" />
</div>
</div>
<p>That is some pretty good performance based on only 6 / 24 joints!</p>
Expand Down Expand Up @@ -2274,17 +2274,17 @@ <h1>Step 9: Model evaluation<a class="headerlink" href="#step-9-model-evaluation
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>*** FITTING: Left Leg
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 77.91%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 76.16%

*** FITTING: Right Leg
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 62.21%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 74.42%

*** FITTING: Left Arm
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 51.74%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 63.95%

*** FITTING: Right Arm
</pre></div>
Expand All @@ -2294,12 +2294,12 @@ <h1>Step 9: Model evaluation<a class="headerlink" href="#step-9-model-evaluation
*** FITTING: Torso
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 81.98%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 75.58%

*** FITTING: Head
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 48.26%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 50.00%
</pre></div>
</div>
</div>
Expand Down Expand Up @@ -2353,44 +2353,44 @@ <h1>Step 9: Model evaluation<a class="headerlink" href="#step-9-model-evaluation
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>*** FITTING: limbs only
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 44.19%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 79.07%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 77.91%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 73.26%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 81.40%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 56.40%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 78.49%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 83.14%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 70.93%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 77.91%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 83.14%
median performance: 78.20%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 71.51%
median performance: 75.58%

*** FITTING: limbs+torso+head
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 73.26%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 85.47%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 82.56%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 80.23%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 78.49%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 87.79%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 88.95%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 71.51%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 78.49%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 36.05%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 80.81%
median performance: 79.65%
median performance: 80.52%
</pre></div>
</div>
</div>
Expand Down
4 changes: 2 additions & 2 deletions projects/modelingsteps/ModelingSteps_10_DL.html

Large diffs are not rendered by default.

16 changes: 8 additions & 8 deletions projects/modelingsteps/ModelingSteps_1through2_DL.html

Large diffs are not rendered by default.

10 changes: 5 additions & 5 deletions projects/modelingsteps/ModelingSteps_3through4_DL.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions projects/modelingsteps/ModelingSteps_5through6_DL.html

Large diffs are not rendered by default.

8 changes: 4 additions & 4 deletions projects/modelingsteps/ModelingSteps_7through9_DL.html

Large diffs are not rendered by default.

Loading

0 comments on commit 647151e

Please sign in to comment.