Delve into PyTorch basics: autograd, model classes, datasets, and data loaders. Gain insights into model development while avoiding common pitfalls. Start creating and training your own PyTorch models.

Deep learning with Pytorch, A beginner's Guide By Daniel Godoy.png

jupyter_final.tar.gz

codesnip1

tensorboard

jupyterp-autograd

jupyterp-computation

jupyterp-rethinking

jupyterp-minibatch

jupyterp-dataloader

jupyterp-evaluation

jupyterp-saveload

jupyterp-predictions

jupyterp-training-predictions

jupyterp-checkpointing

jupyterp-classy

jupyterp-classification

jupyterp-retest

jupyterp-retest-copy

jupyterp-retest-copy-copy

jupyterp-retest-copy-copy-copy

jupyterp-retest-copy-copy-copy-copy

jupyterp-retest-question

jupyterp-retest-question-copy

jupyterp-retest-question-copy-copy

jupyterp-retest-question-copy-copy-copy

jupyterp-retest-question-copy-copy-copy-copy

jupyterp-retest-challenge

jupyterp-retest-challenge-copy

jupyterp-retest-challenge-copy-copy

jupyterp-retest-challenge-copy-copy-copy

jupyterp-retest-challenge-copy-copy-copy-copy

jupyterp-putting1

jupyterp-putting2

jupyterp-putting3

jupyterp-putting4

jupyterp-tensorboard

jupyterp-tensorboard-graphs

jupyterp-tensorboard-scalers

jupyterp-tensorboard-training

GUI-Tensorboard

GUI-Tensorboard-graphs

GUI-Tensorboard-scalers

GUI-Tensorboard-training

GUI-Chapter04

GUI-No-Jupyter-Tensorboard

This course is designed to provide you with an easy-to-follow, structured, incremental, and from-first-principles approach to learning PyTorch. In this course, you’ll be introduced to the fundamentals of PyTorch: autograd, model classes, datasets, data loaders, and more. You will develop, step-by-step, not only the models themselves but also your understanding of them. You'll be shown both the reasoning behind the code and how to avoid some common pitfalls and errors along the way. By the time you finish this course, you’ll have a thorough understanding of the concepts and tools necessary to start developing and training your own models using PyTorch.

Deep Learning with PyTorch Step-by-Step: Part I - Fundamentals

Check all that apply. Which steps are executed inside the gradient descent training loop?

<p>Check all that apply. Which steps are executed inside the gradient descent training loop?</p>


Using all training data points (`N`) to compute the loss.

Using a single data point to compute the loss.

Using `n` (less than `N` but more than one) data points to compute the loss.

What characterizes mini-batch gradient descent?

<p>What characterizes mini-batch gradient descent?</p>


It is faster than batch gradient descent.

It is faster than stochastic gradient descent.

It is more stable than batch gradient descent.

It is more stable than stochastic gradient descent.

Check all that apply. Why is mini-batch gradient descent preferred?

<p>Check all that apply. Why is mini-batch gradient descent preferred?</p>


The gradient is a partial derivative of the loss with respect to parameter `w`.

The gradient is a partial derivative of the error with respect to parameter `w`.

The gradient shows how much the loss changes if parameter `w` changes a little bit.

The gradient shows how much the loss changes if we change all parameters a little bit and at once.

For updating a particular parameter `w`, we need to compute a gradient. Which ones of the statements below are correct?

<p>For updating a particular parameter <code>w</code>, we need to compute a gradient. Which ones of the statements below are correct?</p>


Which learning rates: 

1) Diverge into exploding loss. 
2) Take too long to train .
3) Get stuck with a high loss.

<p>Which learning rates:</p>
<ol>
<li>Diverge into exploding loss.</li>
<li>Take too long to train .</li>
<li>Get stuck with a high loss.</li>
</ol>


When all mini-batches are used for updating the parameters.

When every data point has already been used once for computing the loss.

Check all that apply. When is an epoch complete if we're using mini-batch gradient descent?

<p>Check all that apply. When is an epoch complete if we’re using mini-batch gradient descent?</p>


You have been provided the following data of 5 training examples (`n`):

| x  | y |
|--- |---|
| 2  | 1 |
| 3  | 5 |
| 4  | 9 |
| 5  | 7 | 
| 6  | 4 | 

Consider the linear regression model: `y = b + wx + e`. 

<span style='align: center;'>
Where "e" refers to epsilon (noise) in the above equation,
</span

what is the mean-square error (MSE) that you would expect to obtain when `b = 1`, `w = 1`, and `e = 0`?

<p>You have been provided the following data of 5 training examples (<code>n</code>):</p>
<table>
<thead>
<tr>
<th>x</th>
<th>y</th>
</tr>
</thead>
<tbody>
<tr>
<td>2</td>
<td>1</td>
</tr>
<tr>
<td>3</td>
<td>5</td>
</tr>
<tr>
<td>4</td>
<td>9</td>
</tr>
<tr>
<td>5</td>
<td>7</td>
</tr>
<tr>
<td>6</td>
<td>4</td>
</tr>
</tbody>
</table>
<p>Consider the linear regression model: <code>y = b + wx + e</code>.</p>
<span style='align: center;'>
Where "e" refers to epsilon (noise) in the above equation,
</span
<p>what is the mean-square error (MSE) that you would expect to obtain when <code>b = 1</code>, <code>w = 1</code>, and <code>e = 0</code>?</p>


The loss refers to the difference between the actual value and the predicted value.

For curves with bigger gradients, the size of the learning rate that is chosen should be big. 


In stochastic gradient descent, we end up using all the points (`N`) in the training set to compute the loss. 



Check all that apply. Which of the following statements are correct? 

<p>Check all that apply. Which of the following statements are correct?</p>


You have been provided with the figure given below:

<img src="/udata/W9ZPErxXJY6/data_contour.png" loading="lazy" />

Correctly identify which subplotref ers to the loss surface of the three different scaled data?  

<p>You have been provided with the figure given below:</p>
<img src="/udata/W9ZPErxXJY6/data_contour.png" loading="lazy" />
<p>Correctly identify which subplotref ers to the loss surface of the three different scaled data?</p>


Which of the following figures below illustrates a very big learning rate?

<p>Which of the following figures below illustrates a very big learning rate?</p>


Test your understanding of the concepts explained in this chapter with this quiz!

Introduction

Visualizing Gradient Descent

A Simple Regression Problem

Rethinking the Training Loop

Going Classy

A Simple Classification Problem

Conclusion

Appendix

Quiz