Train Neural Network by loading your images |TensorFlow, CNN, Keras tutorial

Поділитися
Вставка
  • Опубліковано 11 січ 2025

КОМЕНТАРІ • 500

  • @whenmathsmeetcoding1836
    @whenmathsmeetcoding1836  4 роки тому +22

    if you liked the content please support by subscribing 😇
    1. here is the video for multiclass:---- ua-cam.com/video/1Gbcp66yYX4/v-deo.html
    2. here is video for object detection with tensorflow:----- ua-cam.com/video/_TCUPl3j2kI/v-deo.html
    3. here is video for object detection with YoloV3:------ ua-cam.com/video/zm9h4mYymk0/v-deo.html

    • @samesho7190
      @samesho7190 4 роки тому

      Great tutorial!!! thanks. Here, I noticed you didn't normalize your test data, don't you think this might have had a negative impact on your prediction in some way? Since your model was trained and evaluated on normalized data. Although at 1st glance it doesn't seem so.

    • @muhammadtalha2493
      @muhammadtalha2493 3 роки тому

      Hello sir, How to upload only one data set folder like chech happy or not
      no need to check the saad, just happy folder so what channges i have to make in code

    • @muhammadtalha2493
      @muhammadtalha2493 3 роки тому

      i need to check weather this is a plant leaf or not for my semester project so it will alot of help if you tell the code for single data set that the given image is the same or not in testing

    • @bibhuprasaddora1776
      @bibhuprasaddora1776 3 роки тому +5

      Bro please give the code lines link

    • @camilo40
      @camilo40 3 роки тому

      Hi, we use the same pictures in training and validation? or we use diferent?

  • @imanidioli
    @imanidioli 2 роки тому +11

    This is most awesome and most humble tutorial I've ever seen. Despite many other tuts that more like "watch me code" and throwing a line of code with complex variable naming to show off. Thank you.

  • @pronoybiswas3810
    @pronoybiswas3810 2 роки тому +30

    This is the exact tutorial I am looking for. Thank you very much. You described all the steps in the most simplified way. This tutorial will help me a lot in my project so thank you again.

  • @danielpinto1628
    @danielpinto1628 4 роки тому +69

    You know, here in Brazil us IT people praise IT people from your region.

  • @TrendingHashtags-bt7tz
    @TrendingHashtags-bt7tz 10 місяців тому +4

    Crystal clear implementation of CNN

  • @vilakshanpanchal
    @vilakshanpanchal 2 місяці тому +3

    🎯 Key points for quick navigation:
    00:14 *Train a neural network to classify mood (happy/not happy) using custom images from Google Photos.*
    01:34 *Organize images into training, testing, and validation folders for efficient model training.*
    05:31 *Use `ImageDataGenerator` in TensorFlow to preprocess and label images automatically.*
    09:00 *Design a convolutional neural network (CNN) for image classification, including convolutional and max pooling layers.*
    11:19 *Compile and train the model using binary cross-entropy loss and RMSprop optimizer.*
    13:55 *Achieve 100% accuracy on a small dataset; discuss implications and potential improvements.*
    Made with HARPA AI

  • @yepnah3514
    @yepnah3514 4 роки тому +13

    oh god, i spent HOURS trying to figure out my errors. you helped in five minutes!

  • @nonig249
    @nonig249 4 роки тому +10

    After being stuck a whole day, I prayed for wisdom and bumped into your video. You are an answered prayer. Very grateful for your content. Keep at it. #NewSub

  • @Sehmiconductor
    @Sehmiconductor 2 роки тому

    Thank You bro. After building 3 models I forgot the most basic thing, prediction on single random image file. Your video solved my issue. Much love from my side.

  • @inhibited44
    @inhibited44 5 місяців тому

    this is very helpful. I bet if you were picking sad and happy from pictures of friends, the error goes up because too much variation in the photos

  • @KaveeshaNanayakkara99
    @KaveeshaNanayakkara99 Рік тому

    The best video ever for a person who studies deep learning and cnn ❤😍🔥

  • @user-kq5cd7bd3o
    @user-kq5cd7bd3o 4 роки тому +1

    The first working tutorial!!! Thanks a lot

  • @saadalamgir6225
    @saadalamgir6225 3 роки тому

    Model is overfitting and you are happy that ist giving 100% accuracy. OMG

  • @sergiocorrea7889
    @sergiocorrea7889 2 роки тому +3

    Thanks a lot , this is exactly what i was looking for. Great job man!

  • @BoneCrushGaming
    @BoneCrushGaming 3 роки тому +1

    lol... the Neural Network did a good job classifying whether you are happy or not because honestly, I couldn't even tell.

  • @120_sagarikadeb8
    @120_sagarikadeb8 3 роки тому

    This is the best video that I have come so far. Thank you so much Sir!!

  • @sarveshsant5614
    @sarveshsant5614 2 роки тому +2

    Thanks, Man for explaining this in the easiest way🙌

  • @adamcalleja9815
    @adamcalleja9815 Рік тому

    great job explaining it, you're a great teacher

  • @wafazouari7065
    @wafazouari7065 3 роки тому +1

    you are a wonderful human being

  • @sanskritisrivastava2242
    @sanskritisrivastava2242 3 роки тому +7

    Excellent tutorial😍 can’t thank you enough!🙌🏻🔥

  • @EternalNoobCoder
    @EternalNoobCoder 2 роки тому +3

    Exactly what I was looking for. Wonderful video and well explained. Thank You ❤️❤️❤️

  • @cassiemst4993
    @cassiemst4993 4 роки тому +5

    Thank you much for the video!! i really enjoy it and helped me a lot to understand more about CNN

  • @kajalyadav4246
    @kajalyadav4246 Рік тому

    Amazing !! True life saviour. I was looking for exactly the same.

  • @SportSync_official
    @SportSync_official 2 роки тому +3

    Legend, thanks for explaining. i am finally able to put everything i learned about this in practice thanks :)

    • @ousmanealamakaba3135
      @ousmanealamakaba3135 2 роки тому

      hi brother i am confused . i need your help .this lab is important to me?

  • @jitensethi4668
    @jitensethi4668 3 роки тому +2

    Sir I don't know how to express my feelings u are great ❤️❤️ keep going sir

  • @nurulizzahluthfiahnur1122
    @nurulizzahluthfiahnur1122 3 роки тому +2

    Thankyou so much, its really help me, i can use my own image and its awesome

  • @aimanjavid8441
    @aimanjavid8441 3 роки тому

    Superb...
    No word for thanks and appraisal .
    good keep it up

  • @muhammadahmadessa9584
    @muhammadahmadessa9584 Рік тому

    always the low quality videos that are the best out there

  • @JeevaSivalingam
    @JeevaSivalingam Рік тому

    Excellent ji.Really very good explanation with real time image's 🎉🎉🎉

  • @salsabilashraf3713
    @salsabilashraf3713 Рік тому

    Thank you so much for this video. Cannot appreciate enough!

  • @chrisber
    @chrisber 3 роки тому +1

    This is an excellent tutorial, thank you so much!

  • @sanskritisrivastava2242
    @sanskritisrivastava2242 3 роки тому +4

    wonderful tutorial. Thankyou so much. Just one request, Can you pls make a tutorial on how to evaluate this model by confusion matrix,F1score etc?

  • @mageshdanani
    @mageshdanani 4 роки тому +1

    Great bro ...!!! Very good explanation with appropriate pace ...!! Thank you bro !!

  • @nikethatharangi857
    @nikethatharangi857 Рік тому

    this tutorial is really good. thank you so much

  • @LeenaGurgPhysics
    @LeenaGurgPhysics 4 роки тому +4

    Your video is very good. I found it extremely useful. Maybe you could rethink the tags for your video so that it shows up quickly in the search.

  • @sakinamosavi1104
    @sakinamosavi1104 3 роки тому +1

    I really enjoyed. Thanks Sir!!!

  • @jhin5588
    @jhin5588 2 роки тому

    i love you sir, you making it work. So much thanks!

  • @bryan_dx
    @bryan_dx 3 роки тому

    Excellent I just finished it and it recognized most of my images (maybe could it have recognized everyone if I had used more images for training), thanks a lot.

    • @gedekresna3237
      @gedekresna3237 3 роки тому

      there's no "basedata/test" folder isnt it? how you can finished it?

  • @richardmkechera8461
    @richardmkechera8461 2 роки тому

    waoooh ,this is amazing ,thank you brother

  • @jameslucas8369
    @jameslucas8369 Рік тому

    this is the best video ,cong2ln broo

  • @satishb9975
    @satishb9975 2 місяці тому

    Thank you 👍🏻🎉 for easy tutorial of CNn

  • @carloseduardoa.marchiori5598
    @carloseduardoa.marchiori5598 2 роки тому

    Amazing job! Thank you so much for that

  • @johnmuchori6605
    @johnmuchori6605 2 місяці тому

    so helpful.I'm glad Sir

  • @kelvinkipsang3600
    @kelvinkipsang3600 Рік тому

    Very useful and great job, thanks you so much

  • @neilsumanth8013
    @neilsumanth8013 3 роки тому +1

    Thank you very much for this kind of good explanation!

  • @rvrocks1000
    @rvrocks1000 2 роки тому

    Very well explained and to the point

  • @sudhakarp1
    @sudhakarp1 4 роки тому +1

    Very neat explanation, thanks for the video

  • @Rose2369p
    @Rose2369p 2 місяці тому

    The best video ever🙏

  • @monarch6t9
    @monarch6t9 7 місяців тому

    🥰🥰 bhai maja agya thank you vmro

  • @thanhlongnguyen3454
    @thanhlongnguyen3454 3 роки тому +1

    very nice video, good job bro

  • @telabela007
    @telabela007 2 роки тому

    Simply Superb. 🙏🙏

  • @martinhaas4955
    @martinhaas4955 3 роки тому

    Very interesting video, helped me a lot !

  • @rhk1991
    @rhk1991 3 роки тому

    Ty for this video, you help me a lot rn.

  • @James-mu6th
    @James-mu6th Рік тому

    Thx, this is what i looking for.

  • @peterslater2914
    @peterslater2914 10 місяців тому

    Excellent video thanks alot.

  • @jerrymavashev9885
    @jerrymavashev9885 4 місяці тому

    Hey, I like your video a lot. However, at 4:30, how exactly did you call this image from your folder? I can't quite seem to figure it out as you didn't show exactly how you called it. Also, when I type in "img = image.load_img("basedata/train/happy/3.PNG"), it's telling me that the file isn't found and there is no such file, even though there is since I created it. Lastly, when I type in "plt.imshow(img)", it's telling me that the name 'img' is not defined. Please help...I'm following your video and this is throwing me off. Thanks

  • @CarlosRincon
    @CarlosRincon 3 роки тому

    Nice video! thanks man!

  • @sharveensmith9947
    @sharveensmith9947 3 роки тому

    Pls do a tutorial for using and training datasets for Mask RCNN as well, your videos helped alot

  • @sanjaypatil-jq8dh
    @sanjaypatil-jq8dh 4 роки тому +4

    Hello nice video..:)
    2 questions:
    1. Since you have 19 unhappy photos how does batch(3) work here?
    2. Diff. btw batch_size and steps per epoch?

  • @TheBlackNight971
    @TheBlackNight971 4 роки тому +4

    what did u put inside validation folder?

  • @saritham3610
    @saritham3610 4 роки тому +4

    Thank you very much. You made my day .I am happy to learn. Sir please upload more videos. Can you please send me code for model evaluation for same program

  • @guhanesvarmanikandan8769
    @guhanesvarmanikandan8769 4 роки тому +1

    it really helps thank you so much

  • @lalithavanik5022
    @lalithavanik5022 4 роки тому +1

    Thank you for your valuable information sir

  • @anahitabh9649
    @anahitabh9649 2 роки тому

    Amazing,thank you very much

  • @plavali_znaem
    @plavali_znaem 2 роки тому +1

    Sir, I got question regarding where did you save your photos initially? Per my understanding, you have put them into training folder. However, down the video, "there's 11 images in our validation dataset", you're saying at 8:40... I am confused: should I copy images to validation folder, too?

    • @Valessito
      @Valessito Рік тому

      una parte de las imagenes van en el entrenamiento y otra en validacion, yo usaria 75
      25 para cada carpeta

  • @akshaysharmaa7
    @akshaysharmaa7 4 роки тому

    A very nice and informative video sir. Thank yoU !!

  • @siddhantmanna4809
    @siddhantmanna4809 2 роки тому

    Thanks bro, really helped

  • @freadyloaks5339
    @freadyloaks5339 4 роки тому +1

    thankyou very much sir for the great demo,
    but have you the video to explain the details of the models that we have to use for every scenario?

  • @nurulizzahluthfiahnur1122
    @nurulizzahluthfiahnur1122 3 роки тому

    Thankyou so much, its really help me

  • @faku09kpo
    @faku09kpo 3 роки тому

    very useful! thank u so much ;)

  • @kanzoni81
    @kanzoni81 3 роки тому +2

    Need help with
    ValueError: logits and labels must have the same shape ((None, 512) vs (None, 1))

  • @Moahid6
    @Moahid6 3 роки тому +1

    working well, Thank a lot

  • @vandeindia5955
    @vandeindia5955 3 роки тому

    Really helpful sir :)

  • @riyachougule6356
    @riyachougule6356 2 роки тому +1

    Hello sir, it worked really well till model fitting.
    For 'model_fit' step, it is throwing an error called "AttributeError: 'DirectoryIterator' object has no attribute '_assert_compile_was_called' "

    • @Qaidi_804
      @Qaidi_804 2 роки тому

      Did you sort out the issue, and why this error was encountered?

  • @vibhashreehippargi8233
    @vibhashreehippargi8233 Рік тому

    Thanks a lot for the amazing video. I tried it out for healthy and diseased plants, it looks like it wrongly identified few. Should i put them back in training folder and re-run everything again? Please suggest.

  • @REDROSE-be3br
    @REDROSE-be3br 3 роки тому

    Please make videos like this more

  • @joaofonseca528
    @joaofonseca528 3 роки тому +3

    Hello, This helped me a lot but One question what chances would you make if we introduced a third output lets say neutral.
    Thanks

  • @prikarsartam
    @prikarsartam 2 роки тому

    thanks, this helped me!

  • @Nachiket_upadhye_23
    @Nachiket_upadhye_23 2 роки тому

    How to learn machine learning.
    1. watch theory lecture from ocw or other college website
    2. Read blogs and understand maths.
    3. Watch Indian guy doing demo with simple explanations.

  • @nkechiesomonu8764
    @nkechiesomonu8764 2 роки тому

    Thanks a lot, pls can this work with multi-class classification

  • @abiryousuf9931
    @abiryousuf9931 4 роки тому +2

    Thanks for this content brother. helped me a lot. Can you please tell me how i can add more than 2 input classes(for example: happy, not happy, excited,depressed)??

    • @whenmathsmeetcoding1836
      @whenmathsmeetcoding1836  4 роки тому +1

      Sure here is the video for multiclass ua-cam.com/video/1Gbcp66yYX4/v-deo.html

    • @abiryousuf9931
      @abiryousuf9931 4 роки тому

      @@whenmathsmeetcoding1836 But I want to use CNN. Here, you gave class mode='binary'. What can I put here as class mode to take more than 2 classes??

  • @chwenjun225
    @chwenjun225 2 роки тому

    excelent, i just do the same thing with motorbike and car, haha its work

  • @viranchivedpathak4231
    @viranchivedpathak4231 2 роки тому

    Thanks! Very useful

  • @vr-oo7uv
    @vr-oo7uv 4 роки тому +5

    hello sir what is the use of validation folder. can you explain flow_from_directrory and which is compare your photos. i need step by step explanation. This video is very informative but need step by step explanation.

    • @whenmathsmeetcoding1836
      @whenmathsmeetcoding1836  4 роки тому +1

      Sure you may not like your model to overfit on top of training data so on every iteration you have to check the accuracy on unseen data thar comes from the validation folder

  • @rankonanamokoena312
    @rankonanamokoena312 3 роки тому

    Awesome content

  • @sonalisingh9344
    @sonalisingh9344 Рік тому

    Thank you very much sir, you explained step by step. but I have problem in last step. how to accept sub directory path and select both folder data set. please reply me. Thank you.

  • @tomasprager4347
    @tomasprager4347 3 роки тому +1

    Thank you, you are rly master

  • @deekshadheggade1351
    @deekshadheggade1351 3 роки тому

    Can you make leaf disease detection using CNN,keras, DeepLearning

  • @shabnampathan4515
    @shabnampathan4515 4 роки тому +1

    Please make videos on maths for machine learning

    • @whenmathsmeetcoding1836
      @whenmathsmeetcoding1836  4 роки тому

      Sure thanks for suggestion
      also---
      if you want to learn deep learning in depth you can enroll to my udemy courses by following below link, you will get 60% direct discount on the total cost by using this link
      www.udemy.com/course/linear-regression-in-python-statistics-and-coding/?couponCode=AA6866B383F7A9E669C8

    • @shabnampathan4515
      @shabnampathan4515 4 роки тому

      @@whenmathsmeetcoding1836 ok I will check.thanks

    • @shabnampathan4515
      @shabnampathan4515 4 роки тому

      @@whenmathsmeetcoding1836 is there any placement opportunity after doing that course.I know it's me who needs to improve my skills,but if there are placement opportunities from Udemy then it becomes easier to get a job

  • @shilpsshilpa1285
    @shilpsshilpa1285 3 роки тому

    should v need put images in all folders? like testing - in happy 5 images and unhappy 5 images? same for validation too? but high no. of images in training

  • @aimanjavid8441
    @aimanjavid8441 2 роки тому

    Kindly extend to check accuracy on test dataset

  • @calvinatuhaire3116
    @calvinatuhaire3116 2 роки тому

    great tutorial, could you kindly show how to display the results with a confusion matrix?

  • @dody3329
    @dody3329 2 роки тому +1

    sir I did everything like as u have said and I have trained the model but I am facing trouble during testing of a image. Can you kindly help me how should I make the model predict the image class?

  • @deepikasharma952
    @deepikasharma952 2 роки тому

    Nice tutorial
    can mediapipe will provide the accurate results with the guidance of this code? Please provide your Github link...

  • @kishorkandpal3427
    @kishorkandpal3427 3 роки тому

    Great, Jay

  • @aishaakram4270
    @aishaakram4270 3 роки тому

    Thankyou so much for the explanation but I need to train a model for my face recognition project can you please guide how do I train the model for face recognition on both RGB and grey channel. And how can I structure my dataset either multiple folders of people or else?

  • @vaibhavkatiyar7356
    @vaibhavkatiyar7356 2 роки тому

    Good Job

  • @LuffyMonkey0327
    @LuffyMonkey0327 Рік тому

    please do tutorial of this with tarfile. i have tar file image dataset and having trouble opening it

  • @glide1444
    @glide1444 2 роки тому

    thanks for your video ,
    How to save this model

  • @fayezsaeed7991
    @fayezsaeed7991 4 роки тому +5

    Thank you for this good video
    I have one question, in the 'Validation' folder which images did you put?
    are they from train group or test group?

    • @whenmathsmeetcoding1836
      @whenmathsmeetcoding1836  4 роки тому +5

      I had less no of images but yes you should keep all different images in three folders..

    • @plavali_znaem
      @plavali_znaem 2 роки тому

      Got the same question. Did you figure this out? Is that so that I have to save my images to all 6 folders: 2 folders - happy / unhappy -- in every of 3 folders: test, train, validation?