Data Augmentation with TensorFlow's Keras API

In this episode, we'll demonstrate how to use data augmentation on images using TensorFlow's Keras API.

🕒🦎 VIDEO SECTIONS 🦎🕒

00:17 Introduction to Data Augmentation
01:32 Image Augmentation with Keras
08:16 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:
👀 Come say hey to us on OUR VLOG:

[harishakula]

Deeplizard is seriously underrated. Excellent content, beginner friendly. I can definitely see them getting much more popular in the future.

[minhaaj]

I can take her to my grandmother and she'll understand deeplearning! Kudos.

[exploring_the_worlds_water]

This entire series gave me more up to date information on image classification than all of Youtube and the literature combined. My final year project is saved :D thank you so much.

[kifercastillo]

I sincerely think that your videos are the ones that explain the best all the content, i really understand the topics, I''ve watched videos up to 40 minutes long and doesn't explain as well as you do in 9, congratulations and thank you

[pathummathes]

This video series is awesome😍. Madam can you do a video series for object detection

[himalayasinghsheoran]

Thank you for this tutorial and the blog.

[daviddamifogodaramola]

I must Confess, You are really Good. Thanks for your lectures

[suparnarooj]

Hi nice content, can you make a separate video on how to augment only few classes rather than all the classes. It is my concern . This will be majorly helpful for imbalance dataset.

[richarda]

I saw what you did there with the video flipping. Nice touch to illustrate the point :)

[sunbrotheawesome]

Tech-waifu is back UwU . Good lecture. THank youu ! <3

[dewmalfernando]

Hey, how to do this if the colour mode of the images is grayscale? I'm stuck at 4:43

[luq]

I did not know Keras has this function. I did augmentation using OpenCV and os last week. But nice tutorial, thank you so much!

[spacephenix]

Great videos and resources like always!

[GauravSingh-kuxy]

Thanks a lot. Also please make something on object detection. It'll be really helpful.

[lalitsingh]

Thanks for the lecture.Please make a video on GAN

[clementlelievre]

excellent thank you! There is also a video about the ImageDataGenerator object by Laurence Moroney on the Tensorflow channel (although not specifically about it)

[bradyhuang]

Hi Mandy, your tutorials are very informative. I really enjoy it.
I currently work as a RA in school, but I come as a new hand. Your episodes are great.
Would you share some tutorials on R-CNN and how to fine-tune the model in the future?

[osumanaaa]

Thanks for the clear explanations. There is something I'm really curious about, how can we use the TF data augmentation on sequences of images? if we just follow this same method, it will mess up the sequence of images and make it harder to learn from it. is there a way to set a number of frames so that for every N images, we get a corresponding N augmented_images ?

[WheatleyOS]

rotation_range is measured in degrees* small correction but good to know, since a 'rotation_range' of 10 radians would be ridiculously high