MobileNet Image Classification with TensorFlow's Keras API

[@deeplizard]

👉 Check out the blog post and other resources for this video: 🔗 deeplizard.com/learn/video/OO4HD-1wRN8 👀 Come say hey to us on OUR VLOG: 🔗 kzbin.info

[@soroush_thr]

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

[@PatChizzy]

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

[@kseniasidorova9264]

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

[@adi11cr7]

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

[@prashantgupta6885]

Your vlog channel is awesome

[@thibaudplanqueel6933]

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

[@Prathik99]

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.

[@joxa6119]

Where can I get the MobileNet sample images?

[@lenxhhn3724]

u search them yourself

[@marvit9167]

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.

[@HaydenL]

The hardest part will be teaching the network proper Italian hand gestures when making predictions. Maybe add a gesticulate layer to the output?

[@tymothylim6550]

Thank you very much for this educational video! I didn't know much about MobileNet until now! Thank you also for showing the function used to preprocess your images - it helps me understand the sort of file format that Deep Learning models in Keras usually need.

[@Sikuq]

Absolutely great. Thank you.

[@Officer-kd6]

Great video, thank you!

[@ajitegar7738]

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

[@petaca39]

Good video, I want to make some inquiries 1- the image that I want to classify jpg must have a special size or resolution so that MobileNet processes it better 2- you can introduce new classifications or images to MobileNet for example of bacteria since I tried with some images and does not classify them if it is possible how it can be done

[@velmuruganr9321]

This is awesome

[@eduardorabelo3972]

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.

[@georgepalafox5967]

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

[@susantachary7456]

You made my day.. Really Cool Tutorial.

[@lalitsingh5150]

Please make a video on GAN using own dataset

[@abdulwadood6927]

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

[@aishaj4082]

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

[@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 ?

[@giovannicordova4803]

Is Abella Danger now teaching Neural Networks?

[@Mrduirk]

exist for mobilenetv2 a dcgan?

[@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 ??

[@nasrkruithof6372]

Which version of MobileNet is used here?

[@marsrocket]

The MobileNet model in the model zoo uses 300x300 input size. Is the TF version different? If so, is this documented anywhere?

[@deeplizard]

Yes, it uses an input shape of (224,224,3). Documented below in the description of the input_shape parameter. www.tensorflow.org/api_docs/python/tf/keras/applications/MobileNet

[@pulkitaggarwal6130]

I decided to do an image coloring project using CNN, I know what I have to do but don't know how to do it cause it's my first project.

[@wagnersantos7818]

was this episode reposted? I thought I saw him

[@patrickpuentelml4958]

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 :)

[@codechef117]

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: 'data/MobileNet-samples/1.PNG' Please help me.

[@berbatsuleiman]

same problem occurs.

[@rudeviper]

I think this is the cupertino coffee

[@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 ..

[@deeplizard]

Given the name of this channel, the statement was a joke indicating that everyone's top priority should be in studying/knowing all about lizards 🦎

[@tintiniitk]

@@deeplizard Good point. I didn't connect the dots. Guess my mental model is not well trained for such jokes.

[@deeplizard]

Just needs a bit of fine-tuning and transfer learning 😅

[@aguiremedia]

Wait why are you in Vietnam?

[@GauravSingh-ku5xy]

They travel.

[@06_PrathamGarg]

NOT SATISFIED

[@carterhearst]

Are Chris and you siblings or related?

[@mujamilkhan714]

Why you always wear same t-shirt in every video is there any sentiment kinda.????? BTW your videos are awesome 👏🏻

[@deeplizard]

Top secret 🤫