How to Make an Image Classifier – Intro to Deep Learning #6

35 thoughts on “How to Make an Image Classifier – Intro to Deep Learning #6”

1. Hey, I trained a model and when I ran predict on an image, I got [[1. 1. 1.]] as output. What does that mean?

2. Can I use this process for apple defect Multispectral Method for Apple Defect
   
   Detection using Hyperspectral Imaging System ?Im new in image processing

3. You full of life….love the teaching method

4. Can u make a tutorial to classify videos

5. webapp image classifier https://github.com/pengoox/Image-Classifier

6. At 4:09 what did you mean by feature mapping.

7. I just had one doubt. Suppose that we have a filter to detect the curve as shown in the video but the curve is aligned in some direction. How would it still recognize it? Or is it even supposed to?
   In some cases, like identifying an object, the filter should be able to identify the object regardless of it's orientation. While in other cases like identifying numbers, it shouldn't cause it may confuse a 6 with a 9.

8. Awesome. Just fantastic

9. the model.predict method gives out an error, can you help me with it please

10. from parcer import load_data ? where can we find this ?

11. really, a rap session?

12. 0:36 The Humanity Party can make that possible http://www.humanityparty.com

13. It is really very useful!!!! thank you!

14. Sir to be sincere, you're too fast

15. that rap was kinda fire

16. You say 32 by 32 for the first convolution2D added to the model , yet what is the difference if we used 64 by 64. Would we gain resolution in data and accuracy in exchange for more processing time; or is this difference negligible and the results nearly equivalent?

17. What is the best way to make a alphabate classifier.?

    What is better approch using tensor flow only or keras only?

18. Keep rapping! Keep teaching the way you want! +1

19. Youre a god and I love you – thanks a bunch

20. How can I make a neural network to extract the features from images of food wrappers and train the network ? As they don't have any specific shape or type..
    Please reply..

21. y Predict_proba and predict in keras produce same results . I am preparing a htr for english . so i have 26 classes , now i need to get the probabilities for each class . but both predict and predict_proba gives only the predicted class . any solutions . My last activation layer is softmax

22. literally when im running the first block it says.

    importError Traceback(most recent call last)

    importError: cannot import name load_data

    what is going on? any help??

23. hey siraj, u're work's good! but u have been replying to all the comments that praises u but havent been able to answer the question that what does import parser do and what is "load_data"?? plz get back to this

24. At least try to make an effective video: train dataset & detect a certain shape using boundingbox

25. For some reason the load_data command doesn't work anymore.

26. can you teach us this stuff in low level, then go high level

27. Thank you so much for your lecture!

28. Thanks teacher

29. Hello, do you know any intelligence that recognizes hand gestures? I would like to do something like that using an OpenMV cam M7

30. What version of python did you use?

31. Haha Macarena!

32. runn forestt runnnnn

33. I CAME HERE TO LEARN, I LEARNT NOTHING. CLICKBAIT. STACKOVERFLOW WOULD RIP YOU APART.

34. so sad…
    This vdo seems informative but presented steps are too advance to follow (many guidance missing).
    it is not helpful to beginner like me. 🙁

35. How to make a web application for an tensorflow image classifier

Comments are closed.