TensorFlow.js - Examining tensors with the debugger

In this video, we're going to continue our exploration of tensors. Here, we'll be stepping through the code we developed last time with the debugger to see the exact transformations that are happening to our tensors in real-time.

Last time, we went through the process of writing the code to preprocess images for VGG16. Through that process, we gained exposure to working with tensors, transforming and manipulating them.

We're going to now step through these tensor operations with the debugger so we can see these transformations occur in real-time as we interact with our web app.

If you're not already familiar with using a debugger, don't worry, you'll still be able to follow.

We'll first go through this process using the debugger in Visual Studio Code. Then, we'll demo the same process using the debugger built into the Chrome browser.

🕒🦎 VIDEO SECTIONS 🦎🕒

00:30 Help deeplizard add video timestamps - See example in the description
15:13 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.

[deeplizard]

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

[junkmail]

This was the most helpful video I've seen about understanding what tensors are. Thank you and well done!

[joeledwardson]

In case anyone else was struggling to get the debugger in visual studio code to work

1. You need to follow the steps here:
to install the extension "Debugger for Chrome" in visual studio code

2. In visual studio code click "Run" -> "Add Configuration..." -> "Chrome: Launch", it should open a file called "launch.json", then paste the following code:

{
// Use IntelliSense to learn about possible attributes.
// Hover to view descriptions of existing attributes.
"version": "0.2.0",
"configurations": [
{
"type": "pwa-chrome",
"request": "launch",
"name": "Launch Chrome against localhost",
"webRoot": "${workspaceFolder}/static"
}
]
}

3. Make sure you have the server running in a terminal using the command "node server.js" from the "local-server" directory
4. Click "Run" -> "Start Debugging" as illustrated in the video

This will allow you to debug the client "predict.js" code from within visual studio code

[sphynxusa]

Exploring variables like that in Code was awesome and doing the same in Chrome equally impressive. These videos are gems in the dust. Thank you!

[flamboyanz]

Thank you for explaining the debugging features so well. It's going to be very useful in analyzing tensor objects!

[dzundzanify]

where did we get these meanImageNetRGB values?