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

Поделиться
HTML-код
  • Опубликовано: 4 фев 2025

Комментарии • 500

  • @whenmathsmeetcoding1836
    @whenmathsmeetcoding1836  4 года назад +22

    if you liked the content please support by subscribing 😇
    1. here is the video for multiclass:---- ruclips.net/video/1Gbcp66yYX4/видео.html
    2. here is video for object detection with tensorflow:----- ruclips.net/video/_TCUPl3j2kI/видео.html
    3. here is video for object detection with YoloV3:------ ruclips.net/video/zm9h4mYymk0/видео.html

    • @samesho7190
      @samesho7190 4 года назад

      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 года назад

      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 года назад

      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 года назад +5

      Bro please give the code lines link

    • @camilo40
      @camilo40 3 года назад

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

  • @pronoybiswas3810
    @pronoybiswas3810 2 года назад +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.

  • @imanidioli
    @imanidioli 2 года назад +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.

  • @TrendingHashtags-bt7tz
    @TrendingHashtags-bt7tz 11 месяцев назад +4

    Crystal clear implementation of CNN

  • @yepnah3514
    @yepnah3514 4 года назад +13

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

  • @danielpinto1628
    @danielpinto1628 4 года назад +70

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

  • @nonig249
    @nonig249 4 года назад +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

  • @vilakshanpanchal
    @vilakshanpanchal 3 месяца назад +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

  • @KaveeshaNanayakkara99
    @KaveeshaNanayakkara99 Год назад

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

  • @Sehmiconductor
    @Sehmiconductor 2 года назад

    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.

  • @EternalNoobCoder
    @EternalNoobCoder 2 года назад +3

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

  • @sanskritisrivastava2242
    @sanskritisrivastava2242 3 года назад +7

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

  • @inhibited44
    @inhibited44 6 месяцев назад

    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

  • @sarveshsant5614
    @sarveshsant5614 2 года назад +2

    Thanks, Man for explaining this in the easiest way🙌

  • @cassiemst4993
    @cassiemst4993 4 года назад +5

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

  • @sergiocorrea7889
    @sergiocorrea7889 2 года назад +3

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

  • @SportSync_official
    @SportSync_official 2 года назад +3

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

    • @ousmanealamakaba3135
      @ousmanealamakaba3135 2 года назад

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

  • @jitensethi4668
    @jitensethi4668 3 года назад +2

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

  • @BoneCrushGaming
    @BoneCrushGaming 3 года назад +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 года назад

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

  • @user-kq5cd7bd3o
    @user-kq5cd7bd3o 4 года назад +1

    The first working tutorial!!! Thanks a lot

  • @JeevaSivalingam
    @JeevaSivalingam Год назад

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

  • @wafazouari7065
    @wafazouari7065 3 года назад +1

    you are a wonderful human being

  • @adamcalleja9815
    @adamcalleja9815 Год назад

    great job explaining it, you're a great teacher

  • @muhammadahmadessa9584
    @muhammadahmadessa9584 Год назад

    always the low quality videos that are the best out there

  • @LeenaGurgPhysics
    @LeenaGurgPhysics 4 года назад +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.

  • @aimanjavid8441
    @aimanjavid8441 3 года назад

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

  • @kajalyadav4246
    @kajalyadav4246 Год назад

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

  • @nurulizzahluthfiahnur1122
    @nurulizzahluthfiahnur1122 3 года назад +2

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

  • @salsabilashraf3713
    @salsabilashraf3713 Год назад

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

  • @saadalamgir6225
    @saadalamgir6225 3 года назад

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

  • @satishb9975
    @satishb9975 3 месяца назад

    Thank you 👍🏻🎉 for easy tutorial of CNn

  • @mageshdanani
    @mageshdanani 4 года назад +1

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

  • @sanskritisrivastava2242
    @sanskritisrivastava2242 3 года назад +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?

  • @Rati82623
    @Rati82623 3 месяца назад

    The best video ever🙏

  • @bryan_dx
    @bryan_dx 3 года назад

    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 года назад

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

  • @monarch6t9
    @monarch6t9 8 месяцев назад

    🥰🥰 bhai maja agya thank you vmro

  • @chrisber
    @chrisber 3 года назад +1

    This is an excellent tutorial, thank you so much!

  • @jameslucas8369
    @jameslucas8369 Год назад

    this is the best video ,cong2ln broo

  • @thanhlongnguyen3454
    @thanhlongnguyen3454 3 года назад +1

    very nice video, good job bro

  • @nikethatharangi857
    @nikethatharangi857 Год назад

    this tutorial is really good. thank you so much

  • @sakinamosavi1104
    @sakinamosavi1104 3 года назад +1

    I really enjoyed. Thanks Sir!!!

  • @vibhashreehippargi8233
    @vibhashreehippargi8233 Год назад

    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.

  • @jhin5588
    @jhin5588 3 года назад

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

  • @johnmuchori6605
    @johnmuchori6605 3 месяца назад

    so helpful.I'm glad Sir

  • @telabela007
    @telabela007 2 года назад

    Simply Superb. 🙏🙏

  • @TheBlackNight971
    @TheBlackNight971 4 года назад +4

    what did u put inside validation folder?

  • @sonalisingh9344
    @sonalisingh9344 Год назад

    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.

  • @jerrymavashev9885
    @jerrymavashev9885 5 месяцев назад

    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

  • @carloseduardoa.marchiori5598
    @carloseduardoa.marchiori5598 2 года назад

    Amazing job! Thank you so much for that

  • @richardmkechera8461
    @richardmkechera8461 2 года назад

    waoooh ,this is amazing ,thank you brother

  • @rvrocks1000
    @rvrocks1000 2 года назад

    Very well explained and to the point

  • @neilsumanth8013
    @neilsumanth8013 3 года назад +1

    Thank you very much for this kind of good explanation!

  • @sudhakarp1
    @sudhakarp1 4 года назад +1

    Very neat explanation, thanks for the video

  • @riyachougule6356
    @riyachougule6356 2 года назад +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 года назад

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

  • @James-mu6th
    @James-mu6th Год назад

    Thx, this is what i looking for.

  • @PalwinderGill-i4v
    @PalwinderGill-i4v 4 месяца назад

    Sir, i want to know that which model the CNN model used in this video is inspired from?

  • @kelvinkipsang3600
    @kelvinkipsang3600 Год назад

    Very useful and great job, thanks you so much

  • @SadiaAyoub-y8v
    @SadiaAyoub-y8v 2 месяца назад

    Sir, My final year project is related to Automated Fruit Ripeness Detection using Deep Learning model. There will e at least four fruits , we have to train model to classify fruit either Underripe, ripe or overripe. Can you please help me. Can I make a GUI we-based in Flask in Google Collab??? or I should make Web Flask app using VS code and then integrate my model at Google Collab? Which will be more convenient for me?
    One more thing in your video there are two cases(happy or not happy) and you kept it binary. Is there any ternary option available for three classes? underripe, ripe and overipe?

  • @sharveensmith9947
    @sharveensmith9947 3 года назад

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

  • @deekshadheggade1351
    @deekshadheggade1351 3 года назад

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

  • @saritham3610
    @saritham3610 4 года назад +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

  • @古调不弹
    @古调不弹 Год назад

    Hi, excellent tut, but I want to ask a stupid question, do I need to train or test the network using the same person's face photo? thanks

  • @REDROSE-be3br
    @REDROSE-be3br 3 года назад

    Please make videos like this more

  • @plavali_znaem
    @plavali_znaem 2 года назад +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 Год назад

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

  • @nkechiesomonu8764
    @nkechiesomonu8764 2 года назад

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

  • @ancientgear7192
    @ancientgear7192 Год назад

    Very helpfull tutorial. I have some questions though. Shouldnt all the images of the dataset be the same dimensions before we use them? how can i create a confusion matrix?

  • @peterslater2914
    @peterslater2914 11 месяцев назад

    Excellent video thanks alot.

  • @surajwagh3654
    @surajwagh3654 2 года назад

    Supperb 👍

  • @aimanjavid8441
    @aimanjavid8441 2 года назад

    Kindly extend to check accuracy on test dataset

  • @sanjaypatil-jq8dh
    @sanjaypatil-jq8dh 4 года назад +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?

  • @CarlosRincon
    @CarlosRincon 3 года назад

    Nice video! thanks man!

  • @LuffyMonkey0327
    @LuffyMonkey0327 Год назад

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

  • @freadyloaks5339
    @freadyloaks5339 4 года назад +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?

  • @aishaakram4270
    @aishaakram4270 3 года назад

    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?

  • @shilpsshilpa1285
    @shilpsshilpa1285 3 года назад

    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

  • @rhk1991
    @rhk1991 3 года назад

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

  • @lalithavanik5022
    @lalithavanik5022 4 года назад +1

    Thank you for your valuable information sir

  • @guhanesvarmanikandan8769
    @guhanesvarmanikandan8769 4 года назад +1

    it really helps thank you so much

  • @akshaysharmaa7
    @akshaysharmaa7 4 года назад

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

  • @rankonanamokoena312
    @rankonanamokoena312 3 года назад

    Awesome content

  • @vaibhavkatiyar7356
    @vaibhavkatiyar7356 2 года назад

    Good Job

  • @serenataylor8534
    @serenataylor8534 3 года назад

    i am reading a research paper on the visual with CNN. The size of the images is 250*500. The paper used CNN with 100 kernels of size 10*20 for 1st conv layer and 100 kernels of size 20*30 for 2nd layer. Can you expain abit of this as it is not clear to me why the chosen size..what is the effect of the huge filter size

  • @prikarsartam
    @prikarsartam 2 года назад

    thanks, this helped me!

  • @siddhantmanna4809
    @siddhantmanna4809 2 года назад

    Thanks bro, really helped

  • @joaofonseca528
    @joaofonseca528 4 года назад +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

  • @glide1444
    @glide1444 3 года назад

    thanks for your video ,
    How to save this model

  • @anahitabh9649
    @anahitabh9649 2 года назад

    Amazing,thank you very much

  • @kishorkandpal3427
    @kishorkandpal3427 3 года назад

    Great, Jay

  • @martinhaas4955
    @martinhaas4955 3 года назад

    Very interesting video, helped me a lot !

  • @Moahid6
    @Moahid6 3 года назад +1

    working well, Thank a lot

  • @kanzoni81
    @kanzoni81 3 года назад +2

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

  • @shivamdubey4783
    @shivamdubey4783 3 года назад

    sir do we have to sotre photos in all the three folders like validation training and testing or only training

  • @viranchivedpathak4231
    @viranchivedpathak4231 2 года назад

    Thanks! Very useful

  • @dody3329
    @dody3329 2 года назад +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?

  • @nurulizzahluthfiahnur1122
    @nurulizzahluthfiahnur1122 3 года назад

    Can we know what model architecture you use in this model?
    Or this is just a arxhitecture that u made by yourself?

  • @Footballer10309
    @Footballer10309 3 года назад

    Thankyou so much 😍😍

  • @faku09kpo
    @faku09kpo 3 года назад

    very useful! thank u so much ;)

  • @deepikasharma952
    @deepikasharma952 2 года назад

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

  • @mamunhasan8898
    @mamunhasan8898 Год назад

    thanks a lot for your help