HTC Education Series: Deep Learning with PyTorch Basics - Lesson 4

This is the 4th lesson in the HTC Deep Learning with PyTorch Basics course. It begins with the 4th lecture in the Jovian.ai course called 'Deep Learning with PyTorch: Zero to GANs'.

This 4th lecture is called "Image Classification with Convolutional Neural Networks".





What was covered in the lecture

CIFAR10 dataset - 32x32 image dataset for image classification

DataLoaders and torchvision datasets

Understanding convolution

Building a convolutional neural network in a nn.Sequential

    nn.Conv2d

    nn.MaxPool2d

Training a convolutional neural networks

    how to avoid overfitting

Saving and loading model weights


Additional HTC Material

1.  You should start getting more comfortable working with PyTorch DataLoader objects.  It was discussed in the lecture above.  The Paperspace Blog has a good recent post called "A Comprehensive Guide to the DataLoader Class in PyTorch" you can read to further educate yourself about DataLoaders and DataSets.

2.  We will continue our exploration of PyTorch Lightning with this tutorial on"Supervised and Self-Supervised Transfer Learning with PyTorch Lightning".  In addition to giving you more exposure to PyTorch Lightning workflow, this tutorial will cover transfer learning, and self-supervised learning.  

Self-supervised learning is an extremely hot research topic, and provides a way to train a deep learning system when you just have unlabeled data.  Transfer Learning is the key approach to speeding up your custom neural network by piggy-backing on top of an existing pre-trained network.


3.  The first lecture in this lesson introduced convolutional neural networks.  Yann LeCunn pioneered the development of convolutional neural networks in the 80's and beyond.  Learn everything you wanted to know about convolutional neural networks and more from the master in this lecture.



Observations

1.  Each lesson introduces you to new PyTorch functional blocks you can use to construct custom neural net architectures in PyTorch.  This lesson introduced nn.Conv2d and nn.MaxPool2d.

What functional blocks that you already know were also used in this lesson?

2.  Self-supervised learning is an extremely hot deep learning research topic.  It's great that PyTorch lightning has built in features to help you get a handle on it and use it in your own architectures.

There are a number of other HTC posts that discuss self-supervised learning.  Take a browse through some of them to learn more.


Need to review something from the previous lessons in the course. 
No problem.


You can access the first lesson here.

You can access the second lesson here.

You can access the third lesson here.

You just completed lesson 4 here.

Lesson 5 posts next monday.

Keep in mind that HTC courses are works in progress until the final lesson post, so previous and current posted lessons may be tweaked to optimize as the course progresses.



Comments

Post a Comment

Popular posts from this blog

CycleGAN: a GAN architecture for learning unpaired image to image transformations

Image
 Like the Doublemint Twins touting the joys of Doublemint gum, 2 GANs are surely better than 1 GAN.  Especially if we package them together inside of one meta GAN module.  And this is exactly what the CycleGAN architecture does. Have you ever harbored dark secrets of turning a horse into a zebra?  The CycleGAN was developed to do just that. Learn how to turn a horse into a zebra.  And more. Now right away you can notice a difference between the image to image transformation GAN architectures we've been discussing over the last few posts.  Those last few posts described systems that learn from a database of matched input-output image pairs. And if your goal is to turn an edge representation into a nicely filled in continuous tone image, it's easy to build your database of matched input-output image pairs that your GAN system can then learn off of.  Take a continuous tone image (which will be the output of the database pair entry), then run it through an...
Read more

Pix2Pix: a GAN architecture for image to image transformation

Image
 I thought following up yesterday's TraVelGAN post with a Pix2Pix GAN post would be useful to compare what is going on in the 2 architectures.  Two different approaches to the same problem. I stole this Pix2Pix Overview slide below from an excellent deeplearning.ai GAN course (note that they borrowed it from the original paper) because it gives you a good feel for what is going on inside of the Pix2Pix architecture.    Note how the Generator part is very much like an auto-encoder architecture, but rebuilt using the U-Net architecture features (based on skip-connections) that fastai has been discussing in their courses for several years before it became more widely known to the deep learning community at large  (and which originally came from an obscure medical image segmentation paper) . So the Generator in this Pix2Pix GAN is really pretty sophisticated, consisting of a whole image to image auto-encoder network with U-Net skip connections to generate better im...
Read more

Smart Fabrics

Image
"What makes smart fabrics revolutionary is that they have the ability to do many things that traditional fabrics cannot, including communicate, transform, conduct energy and even grow."  This is a quote from Rebeccah Pailes-Friedman, who is a professor at Pratt with a research focus on developing wearable technology and smart textiles. Enhancing textiles can be viewed through different lens.  Enhancements can be aesthetic, or performance boosting, or durability boosting. 
Read more