5.2: Doodle Classifier: Prepping Data in Processing - Intelligence and Learning

[@amanasci2481]

I used to use Python. After I started watching this channel, I am a fan of javascript.

[@Alessandro-nq3tm]

When I saw the numpy format i thought to see The coding Train coding in Python :)

[@LieAngels]

Really enjoying the vid’s lately!

[@TheCodingTrain]

So glad to hear!

[@FuZZbaLLbee]

Now make a generative adversarial network to generate doodles :-)

[@Neworldexport]

fantastic Master Ambassador for Lauren P5*

[@aasimbaig01]

Liked before watching ...

[@КаринаСеменюк-е5ъ]

An OutOfMemoryError means that your code is either using up too much memory because of a bug (e.g. creating an array that's too large, or unintentionally loading thousands of images), or that your sketch may need more memory to run. If your sketch uses a lot of memory (for instance if it loads a lot of data files) you can increase the memory available to your sketch using the Preferences window. OutOfMemoryError: Java heap space

[@HoangTran-jz4rz]

Love all your video

[@grainfrizz]

Hi Dan, on another video, maybe...can we use the Iris dataset in your NN lib? I'm curious how to use / implement the NN lib with inputs that aren't 0-1 value but the output is still a classification vector. Thanks Dan.

[@TheCodingTrain]

Great question! I'd love to talk more about different data sets.

[@grainfrizz]

Thanks Dan. The Iris dataset is free on Wikipedia

[@Sworn973]

You could declare constant for the Width, Height, HeaderSize, than you could do the for loop, image size, etc by the constant, would be more flexible and with less errors, like like 11:52 with X and Y. Sure we got that you was just wanna to show the data, it's wasn't about the code it self.

[@TheCodingTrain]

thanks for the suggestion!

[@nagesh007]

Awesome

[@kotlet.schabowy2133]

1:07 that cat was drawn exactly a year before this video was published

[@vairamuthu2748]

There is already a binary format, why can't we use it?

[@josselinsomervilleroberts2183]

Hi I have a problem with the Neural Network library, I've posted the details on GitHib, in Issues ( Josselin Somerville ) . Could anyone check the code please to tell me if they see anything wrong ?

[@figfox2425]

I don't understand numpy format... we read bytes (8bits) each one is one pixel (28x28) how do you make RGB out of it ? Anyone can answer what i missed here please ? Edit: OK, i got it RGB(byte1,byte1,byte1) If byte is 255 it makes white else it's 0.

[@ramseshendriks2445]

0:55 exactly one year before this video was publiced

[@naveenhettiwaththa5426]

should my data.bin file have 784kb for 1000 of images?

[@arameskchannel]

THE BroGrammer if they are 28x28 images the weight seems correct

[@naveenhettiwaththa5426]

Is it matter to other stuff??? My sketch always give me a 766 kb file And i'm pretty sure that my resolution is 28x28.

[@ryan-heath]

THE BroGrammer 1 kb equals 1024 bytes, so 766kb equals 768.000 bytes

[@muhammedshameel5684]

Make doodle generator generative adversarial networks!

[@RafeedChowdhury]

Best language for machine learning is python... Why don't you use python and do a complicated project? Btw I love your videos! Thanks for sharing your knowledge with us!

[@technicalilm8999]

github.com/pengoox/Doodle_classifier in python

[@zach4216]

false

[@faisalkrnwan]

What im doing here... Im not even know how to code...

[@erokhiin]

try it

[@glenthemann]

num-pie.. not num-pee?????

[@rumbepack]

i thought we were going to see python lol.

[@technicalilm8999]

github.com/pengoox/Doodle_classifier doodle classifier in python

[@SamyHacker]

i appreciate the effort and everything, but do you relise that most ppl that watch these videos are adults, what's with the childish outros.