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 methods should be implemented in a custom model? 

Check all that apply. Which methods should be implemented in a custom model?

Given the partially implemented models below, how many tensors are returned by `MyModel().parameters()`?

```python
class SubModel(nn.Module):
  def __init__(self):
    super().__init__()
    self.w1 = nn.Parameter(torch.randn(1, dtype=torch.float))
    self.w2 = nn.Parameter(torch.randn(1, dtype=torch.float))

class MyModel(nn.Module):
  def __init__(self):
    super().__init__()
    self.linear = nn.Linear(1, 1, bias=False)
    self.sub = SubModel()
```

Given the partially implemented models below, how many tensors are returned by <code>MyModel().parameters()</code>?
<pre><code class="language-python">class SubModel(nn.Module):
 def __init__(self):
 super().__init__()
 self.w1 = nn.Parameter(torch.randn(1, dtype=torch.float))
 self.w2 = nn.Parameter(torch.randn(1, dtype=torch.float))

class MyModel(nn.Module):
 def __init__(self):
 super().__init__()
 self.linear = nn.Linear(1, 1, bias=False)
 self.sub = SubModel()
</code></pre>

What's the recommended way of performing the forward pass in a model?

What’s the recommended way of performing the forward pass in a model?

Given the snippet below, what is the output produced by calling `model(x)`?

```python
x = torch.randn(10, 1)
model = nn.Sequential(nn.Linear(1, 1))
model.to('cuda')
```

Given the snippet below, what is the output produced by calling <code>model(x)</code>?
<pre><code class="language-python">x = torch.randn(10, 1)
model = nn.Sequential(nn.Linear(1, 1))
model.to('cuda')
</code></pre>

What's the purpose of calling `model.train()`?

What’s the purpose of calling <code>model.train()</code>?

Check all that apply. Which elements have a state dictionary? 

Check all that apply. Which elements have a state dictionary?

Given the sequential linear model below, how many tensors are returned by `model.parameters()`?

```python
device = 'cuda' if torch.cuda.is_available() else 'cpu'
model = nn.Sequential(nn.Linear(1, 1)).to(device)
```

Given the sequential linear model below, how many tensors are returned by <code>model.parameters()</code>?
<pre><code class="language-python">device = 'cuda' if torch.cuda.is_available() else 'cpu'
model = nn.Sequential(nn.Linear(1, 1)).to(device)
</code></pre>

1) `model.train()`
2) `optimizer.step()`
3) `loss.backward()`

1) `loss.backward()`
2) `optimizer.step()`
3) `model.train()`

1) `model.train()`
2) `loss.backward()`
3) `optimizer.step()`

1) `optimizer.step()`
2) `loss.backward()`
3) `model.train()`

You have been provided with the following code snippet:

```python
torch.manual_seed(42)
model = nn.Sequential(nn.Linear(1, 1)).to(device)        
optimizer = optim.SGD(model.parameters(), lr=lr)
loss_fn = nn.MSELoss(reduction='mean')

for epoch in range(n_epochs):
    1) ....                

    yhat = model(x_train_tensor)                   
    
    loss = loss_fn(yhat, y_train_tensor)

    2) ....
    
    3) ....
    optimizer.zero_grad()
```

Using the choices given below, fill in the blanks by selecting the correct options at their respective places:

You have been provided with the following code snippet:
<pre><code class="language-python">torch.manual_seed(42)
model = nn.Sequential(nn.Linear(1, 1)).to(device) 
optimizer = optim.SGD(model.parameters(), lr=lr)
loss_fn = nn.MSELoss(reduction='mean')

for epoch in range(n_epochs):
 1) .... 

 yhat = model(x_train_tensor) 
 
 loss = loss_fn(yhat, y_train_tensor)

 2) ....
 
 3) ....
 optimizer.zero_grad()
</code></pre>
Using the choices given below, fill in the blanks by selecting the correct options at their respective places:

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