Learn and practice PyTorch, a framework for developing deep learning models.

Become a Deep Learning Professional

In this module, we’ll be introduced to the fundamentals of PyTorch: autograd, model classes, datasets, data loaders, and more. We’ll develop models and understand them step-by-step. We'll understand the reasoning behind the code and how to avoid some common pitfalls and errors along the way.
By the time we finish this module, we’ll have a thorough understanding of the concepts and tools necessary to start developing and training our own models using PyTorch.

Deep Learning with PyTorch

What will be the output of the following code?

```python
class Scores:
    def __init__(self, s1, s2):
      self.scores = s1 + s2
    def display(self, scores):
      print(scores)
 
x = Scores(5,10)
setattr(x, 'scores', x.scores+1)
x.display(x.scores)
```

What will be the output of the following code?
<pre><code class="language-python">class Scores:
 def __init__(self, s1, s2):
 self.scores = s1 + s2
 def display(self, scores):
 print(scores)
 
x = Scores(5,10)
setattr(x, 'scores', x.scores+1)
x.display(x.scores)
</code></pre>

Methods that start with a single underscore (`_make_train_step()`) are known as private methods. 

Methods that start with a single underscore (<code>_make_train_step()</code>) are known as private methods.

Marcus Jones

`AttributeError: 'Students' object has no attribute '__studentrollno'`

`AttributeError: 'Students' object has no attribute '_studentname'`

What will be the output of the following?

```python
class Students(object):
  def __init__(self):
    self._studentname = "Marcus Jones"
    self.__studentrollno = 202111700

std = Students()
print(std._studentname)
print(std.__studentrollno)
```

What will be the output of the following?
<pre><code class="language-python">class Students(object):
 def __init__(self):
 self._studentname = &quot;Marcus Jones&quot;
 self.__studentrollno = 202111700

std = Students()
print(std._studentname)
print(std.__studentrollno)
</code></pre>

The placeholder attribute of a class is also known by "delayed arguments."

The placeholder attribute of a class is also known by “delayed arguments.”

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

Appendix

Conclusion

Quiz