Loading in your own data – Deep Learning basics with Python, TensorFlow and Keras p.2

42 thoughts on “Loading in your own data – Deep Learning basics with Python, TensorFlow and Keras p.2”

1. Could u plz provide me caption so that I can understand easily

2. This was the most helpful video I've found. thank you!

3. how can i please convert all the pictures into dataframe of pixel ?

4. sent how i can do one for words

5. I am trying to find my dataset on mac but keep getting an error that says FileNotFoundError. Is it because it's in the cloud? How to fix this?

6. you look like Snowden man

7. Do the class numbers have to be 0 and 1? I've been using a tf model with OpenCV to find a cat or dog with a live video, but the model predicts 0 when there is a dog or if neither class is found.

   I tried changing class_num from 0 to another integer to differentiate dog predicted from neither predicted, but then the model comes out terrible. Any way around this?

8. The amount of troubleshooting that I have to do with Python code is frustrating af. There should be whole tutorials on why python never works. smh

9. Thank you so much for this video. As a programmer who just wants to start prototyping a simple model without a great DL background this video gave me the tools to get on with my work.

10. So far, so good! The first dog grayscale image was successfully displayed. I was getting nervous there for a minute! I got confused when you added all that space at the bottom. It threw off my Jupyter notebook. I followed you thereafter, but my output did not print. We'll on to the other videos from other channels. I got to keep moving on. It was good while it lasted.

11. Great Video !!

12. Sentdex: understands neural nets
    Also Sentdex: doesn't know what to call a dogs paw

13. I have an error for some reason and in the start when i try to show the image of dog from the path of "C:/Desktop/Dataset/Dog " it says No such file or directory: 'C:/Desktop'.Could yoy help me please

14. The "paw"

15. 5:04 heh blue dog

16. X and y numpy array shapes don't match when I try to load RGB images for training data. Can you please help?

17. Has the .reshape() problem in Keras been fixed or does it still exist?

18. using training_data.append() is taking a whole eternity for me what should i do to make it more efficient??…
    the dog and cat data I am using is 25000 images

19. Sir i have a question, how can I load and access a dataset with multiple sub classes. For example: a leaf dataset with 7types(7classes) of leaf and all of them have two subclass(healthy and unhealthy), how can i load and access all of the images. It will be so helpfull if you tell me, thank you.

20. Hi, great work!
    I have a question, though, upon the "homework challenge" !
    reshape(-1, IMG_SIZE, IMG_SIZE, 3) pops a ValueError: cannot reshape array of size 239640576 into shape (224,244,3).

    What's your opinion and solution ??
    Thank you

21. Only half of my data is in my training_data

22. Create_training_data only messes up my data size

23. Hello, according to syntax, does the network first familiarize itself with a dog before moving onto the pictures of cat and doing the same ?

24. Nice Video……. But when done with google collab, takes a bit of time

25. Excellent work

26. Something wrong with "import os" or with "os.listdir(path)", it says that there is no directory and I dont know why
    And yes the path I put in is correct

27. Extracting the zipfile to another file just takes too long

28. The output of X[1]
    for me is 1 idk why

29. How do you build training data if you have imbalance problem?

30. Oh thank you! I've looking for the way to load my own dataset and here you go! :З

31. Can you explain why is that -1 used in reshape

32. For those who want to use RGB/color images, modify these lines!
    Change these:
    img_array = cv2.imread(os.path.join(path,img) ,cv2.IMREAD_GRAYSCALE)
    plt.imshow(img_array, cmap='gray')
    X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)

    To:
    img_array = cv2.imread(os.path.join(path,img))
    plt.imshow(img_array)
    X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 3)

    And this should work, good luck!

33. I keep Getting:
    error: (-215:Assertion failed) !ssize.empty() in function 'cv::resize'
    What does it mean, could not find anything on the web, help!

34. Is this applicable for clasifying snake breed

35. Dear the artificial intelligence community
    I am pleased to introduce DIDA dataset, which is the largest handwritten digit dataset. I will be grateful, if you could help me to introduce this dataset to the community.
    Thanks

36. Thank you for sharing, Sir. Sir, can you share how to deploy this CNN object detection to raspberry pi 4B?

37. THANK YOU SO MUCH!!! I just started with Machine Learning and Neural Networks and this video helped me a lot!!!

38. Having a little trouble wrapping my head around labeling my training data.

    I have a problem with around 50k classes, and the output could only be one of those classes. What would be my best approach to labeling my data, would it be one-hot encoding, or do I go ahead and jam these classes between 0 and 1?

39. What would be the differences if there were more than 2 classes?

40. At 4:46 getting message that 'img_array' not defined, same exact code…

41. I LOVE YOU MAN

42. What the dog doing?

Comments are closed.