MobileNet Image Classification with TensorFlow's Keras API

In this episode, we'll introduce MobileNets, a class of light weight deep convolutional neural networks that are vastly smaller in size and faster in performance than many other popular models. We'll also see how we can work with MobileNets in code using TensorFlow's Keras API.

🕒🦎 VIDEO SECTIONS 🦎🕒

00:17 Intro to MobileNets
02:56 Accessing MobileNet with Keras
07:25 Getting Predictions from MobileNet
13:33 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:

[kseniasidorova]

Thank you so much for the whole series, the best explanation of CNN in Keras I could ever wish for!

[soroush_thr]

Ma'am, you are brilliant! YouTube needs more people like you.

[joxa]

Where can I get the MobileNet sample images?

[marvit]

That is definitively a cappuccino. There is still a long way to go before we get a full-fledged artificial Italian lol. Anyway nice video and fantastic channel. Keep up the good work.

[ajitegar]

Hi Mandy, I have a problems mobilenetV2 from fine tuning. In the decode_predictions` expects ' 'a batch of predictions ' '(i.e. a 2D array of shape (samples, 1000)). ' 'Found array with shape: (1, 3). How is the solution ?.
Thanks

[eduardorabelo]

Am I late to ask about the samples of this video? I really dont understand how can i get the MobileNet-samples used in the function prepare_image.

[abdulwadood]

Had to Use, below 2:
from keras.preprocessing import image
from keras.applications import imagenet_utils
to avoid following errors:
"NameError: name 'imagenet_utils' is not defined"
"NameError: name 'image' is not defined"

Also my confusion matrix TN and TP are not coming in high even after VGG16 fine tune-ing

[lalitsingh]

Please make a video on GAN using own dataset

[Prathik]

Please make a video on using differential learning rates for transfer learning in keras and the best practices to be followed for fine tuning the mobile net.

[PatChizzy]

I've read articles on mobilenet, none gave me such great insight as this 14mins video. Really amazing. Thank you

[georgepalafox]

Awesome video! Do u have videos on GANs? Looking for a tutorial. Thx.

[adicr]

Day 1 on this channel, already in love with it.

[AbdullahJirjees]

I have around 10000 images database and I did the annotation and I created the .CSV file, How Can I use it with MobileNet ?

[thibaudplanqueel]

I've learn a lot about deep learning by watching this channel, thanks for this great work !
It was helping me a lot to understand basics in computer vision.
Best regards

[patrickpuentelml]

Hi Miss can you do a video training your own custom object detector for a especific object using Mobilenet SSD ? Please
Thanks for share the theory I love it :)

[ragavkishoreg]

I am thinking about doing a project based on this ? Could you tell me what basic should I know of ML and Deep learning before I can understand this and implement project based on MobileNets ??

[codechef]

Image(filename='data/MobileNet-samples/1.PNG', width=300, height=200)
I am getting error on this line

FileNotFoundError: [Errno 2] No such file or directory:
Please help me.

[tintiniitk]

8:59 : "If you are not aware. And I don't know how you can not be aware of this...". Umm, I am not an American, so ..

[aishaj]

Hi, Can MobileNets be used for short sound file ( 2 -3 seconds) if it is converted to spectrograms ?