Solving real world data science problems with Python! (computer vision edition)

Practice your Python Pandas data science skills with problems on StrataScratch!
stratascratch.com/?via=keith
In this video we work on a real world computer vision problem using Python. The problem task is to create a model that can distinguish a flower known as “La Eterna” from other types of flowers.
To do this we create convolutional neural networks (CNNs) using the Tensorflow/Keras libraries. We examine how to create a simple model and then improve it using techniques such as data augmentation & preprocessing. We play around with different types of network architectures and see how changes improve or decrease overall task performance.
Link to source code (Github):
github.com/KeithGalli/Unlocke...
Link to HP challenge:
www.hp.com/us-en/workstations...
My previous videos on neural networks!
Intro to neural nets: • Introduction to Neural...
Real-world tutorial: • Real-World Python Neur...
** I've left a bunch of additional useful resources in the README of the Github repo **
Videography for clips I integrated at the start by Ryan Cabana
www.ryancabana.com/
Hopefully you enjoy this video! Please leave it a like & subscribe if you did :).
If you have questions about topics covered in this video, please let me know in the comments.
-------------------------
Follow me on social media!
Instagram | / keithgalli
Twitter | / keithgalli
-------------------------
Song at the end
good morning by Amine Maxwell / aminemaxwell
Creative Commons - Attribution 3.0 Unported - CC BY 3.0
Free Download / Stream: bit.ly/2vpruoY
Music promoted by Audio Library • Good morning - Amine M...
-------------------------
If you are curious to learn how I make my tutorials, check out this video: • How to Make a High Qua...
Practice your Python Pandas data science skills with problems on StrataScratch!
stratascratch.com/?via=keith
Join the Python Army to get access to perks!
KZbin - / @keithgalli
Patreon - / keithgalli
*I use affiliate links on the products that I recommend. I may earn a purchase commission or a referral bonus from the usage of these links.
-------------------------
Video timeline!
0:00 - Intro
0:40 - Video overview (what we’ll be working on)
1:53 - Code setup (GitHub repo & HP challenge link)
5:11 - Exploring the dataset that we’ll be using
6:20 - Reviewing template code (starter-code.ipynb)
8:53 - Installing necessary Python libraries (opencv-python, tensorflow)
10:31 - Reviewing template code (part 2)
11:03 - How we load in the dataset (ImageDataGenerator, flow_from_directory)
14:33 - Building our first classifier (convolutional neural net - CNN)
25:19 - Methods to improve neural network performance (MaxPooling, dropout, network architecture)
29:30 - Quick discussion about importance of precision & recall versus accuracy
32:35 - Data augmentation & preprocessing (another way to improve performance)
47:15 - Programmatically finding the best neural network architectures (Keras Tuner)
1:20:00 - Video recap & conclusion

[@KeithGalli]

Sorry for the delay in getting this video posted! I think it's a good one though so hopefully it's worth the wait :)

[@mingyuancheng3458]

thank you guy

[@KeithGalli]

@@mingyuancheng3458 you're welcome!!

[@rosnawatiabdulkudus6435]

Thank you 😊

[@ilan_kayesar]

Hey man, haven't seen your channel in a while, just so you know back when I was like in the 5th grade I would watch your python tutorials which taught me how to code, this year I'm in the 9th grade and have been accepted into the best academy for code in my country, you have made an incredible impact on my life, keep it up!

[@lordfarquad1530]

ok jew

[@satchsumner-waldman8761]

@@lordfarquad1530 are u fr man shut up

[@itsReshad]

Finally! Love your content, you teach and explain really well, I have learned tonnes from following along with you!

[@dr.shefalisadvice5649]

The best thing about you is that you provide all the dataset's that you have used in your videos not like other channels on KZbin who just teach data manipulation but don't give us the data set they have used thank you so much man...

[@ahmedsamy-ug5bv]

thanks, please keep posting similar videos for real world projects, Its very useful

[@kirubaselvi6754]

Loved the intro and you are the best in teaching these things✨

[@Kevin-gm7gx]

Hee is back !! Thanks Keith - your content is really awesome, thanks for posting this :)

[@dasmutterhaus]

Oh Keith we can see you having fun! That is great! Loved the intro

[@KeithGalli]

😊

[@lautaroperez]

Another great video! Greetings from Argentina!

[@wahaha108]

Great job! This series (solving real world data science problems) really differentiate your video fro m others.

[@KeithGalli]

Glad you enjoy 😊

[@MM-uh2qk]

Great video. Very well done! Will setting the metric to "F1 score" serve the same purpose as ["precision", "recall"]? Which one works better to prevent false evaluation resulting from class imbalance?

[@nosinibnamahbub5270]

Love your content. Would you please make segmentation related task using pytorch

[@danieldiaz2164]

Very informational video, and you make new topics sound less intimidating for beginners. Thanks

[@KeithGalli]

You're welcome!

[@mehdismaeili3743]

Hi, thanks for this great video, you are a very good teacher.

[@KeithGalli]

Thank you!!

[@Paperscissor183]

Great vid. Is it possible to use people 's images like actors faces and it tells you their names just by using facial data?

[@himanshuverma8648]

Can you please do a video on real time ML project involving extensive EDA. It would be very much helpful and interesting to learn.

[@yodude8325]

Finally! Yay

[@luyckr356]

Hi Keith, are you using the WSL Manager by Bostrot?

[@dongliang7158]

Nice work, Keith. I’m trying to locate this video with one of your playlist channels, but couldn’t find it(especially not in one called ‘data science’). So could you please tell me how I can find the channel for some similar videos?

[@KeithGalli]

Hmm I don't quite understand what you are asking. Check the video description, I left a couple similar videos there!

[@jacktrainer4387]

Not using a Mac?! Anaconda is definitely the way to go on a Mac. I think they still use it in 6.001x & 6.002x. If there is no conda install command for a package, you can still use pip install w/o a problem. This looks like a fun data set. Looking forward to trying it!

[@KeithGalli]

hahahahah sorry to disappoint xD. Hope you enjoy the video thought!

[@KeithGalli]

btw, thank you so much for the extremely generous donation on buymeacoffee!! That was awesome to wake up to today :)

[@enricomassignani]

If you crop the images, does the size of array representing them change?

[@bernardorodriguezarmida2970]

this guy deserves to be the god of python !!

[@FutureForward-ic5rf]

is this good to do as a project for a machine learning assingment project ?

[@satchsumner-waldman8761]

love the text from mom lmao

[@asmafaraj3285]

Hallo, I am trying to evaluate submission data set. 1. is it equal to test data set? 2. and how to get the true_labels ?

[@fustigate8933]

yayayyay

[@razorgen4]

Bro, are you in fight club?? Why you always beat up hahahaha

[@KeithGalli]

Lol 😆. Not a fight club, but I play ice hockey so it's similar!

[@AshishSingh-753]

Your model cannot detect me

[@berrodriquez26]

This guy deserves to be next to God

[@logannon]

how much RAM does your computer have?

[@KeithGalli]

16gb RAM

[@logannon]

@@KeithGalli thank you. i want to run something similar and wanted to see if i needed to add memory. your videos are awesome, man. i learn a lot. thanks as always.

[@KeithGalli]

@@logannon Thanks for the kind words! :)

[@eiyrm]

yo yo please share this desktop wallpaper :)

[@anonviewerciv]

21:31 Buy more GPUs.