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
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.
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
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
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.
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.
🎯 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
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
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.
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.
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
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
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?
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' "
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.
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.
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)??
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.
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
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.
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
@@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
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
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?
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?
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?
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
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.
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
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
Bro please give the code lines link
Hi, we use the same pictures in training and validation? or we use diferent?
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.
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.
You know, here in Brazil us IT people praise IT people from your region.
Crystal clear implementation of CNN
🎯 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
oh god, i spent HOURS trying to figure out my errors. you helped in five minutes!
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
You are so welcome
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.
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
The best video ever for a person who studies deep learning and cnn ❤😍🔥
The first working tutorial!!! Thanks a lot
Model is overfitting and you are happy that ist giving 100% accuracy. OMG
Thanks a lot , this is exactly what i was looking for. Great job man!
lol... the Neural Network did a good job classifying whether you are happy or not because honestly, I couldn't even tell.
This is the best video that I have come so far. Thank you so much Sir!!
Thanks, Man for explaining this in the easiest way🙌
great job explaining it, you're a great teacher
you are a wonderful human being
Excellent tutorial😍 can’t thank you enough!🙌🏻🔥
Exactly what I was looking for. Wonderful video and well explained. Thank You ❤️❤️❤️
Thank you much for the video!! i really enjoy it and helped me a lot to understand more about CNN
Amazing !! True life saviour. I was looking for exactly the same.
Legend, thanks for explaining. i am finally able to put everything i learned about this in practice thanks :)
hi brother i am confused . i need your help .this lab is important to me?
Sir I don't know how to express my feelings u are great ❤️❤️ keep going sir
Thankyou so much, its really help me, i can use my own image and its awesome
Superb...
No word for thanks and appraisal .
good keep it up
always the low quality videos that are the best out there
Excellent ji.Really very good explanation with real time image's 🎉🎉🎉
Thank you so much for this video. Cannot appreciate enough!
This is an excellent tutorial, thank you so much!
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?
Great bro ...!!! Very good explanation with appropriate pace ...!! Thank you bro !!
Glad you liked it!
this tutorial is really good. thank you so much
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.
I really enjoyed. Thanks Sir!!!
Glad you enjoyed it!
i love you sir, you making it work. So much thanks!
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.
there's no "basedata/test" folder isnt it? how you can finished it?
waoooh ,this is amazing ,thank you brother
this is the best video ,cong2ln broo
Thank you 👍🏻🎉 for easy tutorial of CNn
Amazing job! Thank you so much for that
so helpful.I'm glad Sir
Very useful and great job, thanks you so much
Thank you very much for this kind of good explanation!
You are welcome!
Very well explained and to the point
Very neat explanation, thanks for the video
Glad it was helpful!
The best video ever🙏
🥰🥰 bhai maja agya thank you vmro
very nice video, good job bro
Thank you 👍
Simply Superb. 🙏🙏
Very interesting video, helped me a lot !
Ty for this video, you help me a lot rn.
Thx, this is what i looking for.
Excellent video thanks alot.
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
Nice video! thanks man!
Pls do a tutorial for using and training datasets for Mask RCNN as well, your videos helped alot
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?
what did u put inside validation folder?
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
Yes, sure
it really helps thank you so much
Glad to hear that!
Thank you for your valuable information sir
Thanks and welcome
Amazing,thank you very much
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?
una parte de las imagenes van en el entrenamiento y otra en validacion, yo usaria 75
25 para cada carpeta
A very nice and informative video sir. Thank yoU !!
So nice of you
Thanks bro, really helped
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?
Yes, soon
Thankyou so much, its really help me
Most welcome 😊
very useful! thank u so much ;)
Need help with
ValueError: logits and labels must have the same shape ((None, 512) vs (None, 1))
working well, Thank a lot
Glad to hear that
Really helpful sir :)
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' "
Did you sort out the issue, and why this error was encountered?
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.
Please make videos like this more
Hello, This helped me a lot but One question what chances would you make if we introduced a third output lets say neutral.
Thanks
thanks, this helped me!
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.
Thanks a lot, pls can this work with multi-class classification
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)??
Sure here is the video for multiclass ua-cam.com/video/1Gbcp66yYX4/v-deo.html
@@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??
excelent, i just do the same thing with motorbike and car, haha its work
Thanks! Very useful
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.
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
Awesome content
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.
Thank you, you are rly master
Glad it helped
Can you make leaf disease detection using CNN,keras, DeepLearning
Please make videos on maths for machine learning
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
@@whenmathsmeetcoding1836 ok I will check.thanks
@@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
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
Kindly extend to check accuracy on test dataset
great tutorial, could you kindly show how to display the results with a confusion matrix?
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?
Nice tutorial
can mediapipe will provide the accurate results with the guidance of this code? Please provide your Github link...
Great, Jay
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?
Good Job
please do tutorial of this with tarfile. i have tar file image dataset and having trouble opening it
thanks for your video ,
How to save this model
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?
I had less no of images but yes you should keep all different images in three folders..
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?