PyTorch DataLoader Source Code - Debugging Session

In this episode, we debug the PyTorch DataLoader to see how data is pulled from a PyTorch data set and is normalized. We see the impact of several of the constructor parameters and see how the batch is built.

🕒🦎 VIDEO SECTIONS 🦎🕒

00:45 Overview of Program Code
03:12 How to Use Zen Mode
03:56 Start the Debugging Process
04:38 Initializing the Sampler Based on the Shuffle Parameter
05:35 Debugging next(iter(dataloader))
07:57 Building the Batch Using the Batch Size
10:37 Get the Elements from Dataset
18:43 Tensor to PIL Image
21:48 Collective Intelligence and the DEEPLIZARD HIVEMIND

💥🦎 DEEPLIZARD COMMUNITY RESOURCES 🦎💥

👋 Hey, we're Chris and Mandy, the creators of deeplizard!

👉 Check out the website for more learning material:

💻 ENROLL TO GET DOWNLOAD ACCESS TO CODE FILES

🧠 Support collective intelligence, join the deeplizard hivemind:

🧠 Use code DEEPLIZARD at checkout to receive 15% off your first Neurohacker order
👉 Use your receipt from Neurohacker to get a discount on deeplizard courses

👀 CHECK OUT OUR VLOG:

❤️🦎 Special thanks to the following polymaths of the deeplizard hivemind:
Tammy
Mano Prime
Ling Li

🚀 Boost collective intelligence by sharing this video on social media!

👀 Follow deeplizard:

🎓 Deep Learning with deeplizard:

🎓 Other Courses:

🛒 Check out products deeplizard recommends on Amazon:

🎵 deeplizard uses music by Kevin MacLeod

❤️ Please use the knowledge gained from deeplizard content for good, not evil.

[sadam]

thanks for doing these video. I really like old format of videos with photo of the speaker - also where is the voice of the wisdom or was it the voice of the lizard - that was awesome

[RedShipsofSpainAgain]

Excellent joke at 8:01 with the sneaky sunglasses and skull swap!

[jerekabi]

This has really helped in understanding how the samplers work. Thanks a lot

[shivamroy]

Real quality content, please keep making these videos.

[deeplizard]

👉 Check out the blog post and other resources for this video:

👀 Come say hey to us on OUR VLOG:

[datame]

What a fantastic subject! Very well explained.
Are you still traveling? Please take care of yourselves! We really need your videos and good advice to become data scientists. Thanks for your great work!

[ayyappahemanth]

Nice video, please do more and more videos

[vornam_nachnam_]

Hi Chris / deeplizard team, great series of videos, thanks a lot for your effort!
I have a general question concerning image preprocessing. The MNIST / Fashion MNIST datasets have images of the same resolution. But in "real life", when you gather some images, they are unlikely to have the same size. What is the best strategy to handle that? Should we downscale all images to the smallest resolution? Upscale all to the highest in the dataset? Or are there some network architectures which are able to deal with varying sizes?

[昊时]

Helps a lot！I will recommend it to all my friends.

[elvykamunyokomanunebo]

This is cool,
Is it possible to pass feature names as well to the DataLoader?
Let's say if I want to perform feature importance, is this possible?

[tehreemsyed]

Hi, I have a question regarding data_loaders. I want to do batch training, and for that I need to give our data in the form of batches, but we need to extract specific columns from dataloader as we are training physics informed neural network. I want to access below columns or features from the data_loader:
t_train = torch.tensor(train[:, :, 0])
u_train = torch.tensor(train[:, :, 1:-1])
x_train = torch.tensor(train[:, :, 3])
t_test = torch.tensor(test[:, :, 0])
u_test = torch.tensor(test[:, :, 1:-1])
x_test = torch.tensor(test[:, :, 3])
How can I access a specific column from a data_loader and give these to the model while training?
I appreciate any help you can provide.
Thank you.

[zwhitchcox]

You can "step out" of code too if you accidentally step into it.