How To Train Deep Learning Models In Google Colab- Must For Everyone

47 thoughts on “How To Train Deep Learning Models In Google Colab- Must For Everyone”

1. Why Batch Size is 16 (not 32).
   How to determine the batch_size in general??
   Thanks

2. Getting error in epocs parts- "Failed to get Convulation algorithm".
   what to do.?

3. Please show me the confusion matrix for this project…plz plz plz

4. When i connect to a gpu model through error.

5. i am getting error .. i have run the same code as yours.. but while running the epoch.. it is showing failed to get convolution algorithm

6. i have error in >>> model=load_model('model_resnet50.h5')

7. How do we work with image recognition by creating our own image dataset?

8. Do i need to have cuda installed in my workstation to run Google Colab and train the model?

9. Regarding ads,,,
   I Couldn't find any logic to show this kinda anti-islamic ads.Without any precise knowledge about islam just showing a verse,humiliating Al-Quran here it's trying to prove Islam is wrong.How stupid!!!
   You want to leave, you leave.How do you dare to demotivate others publicly spreading hatred particularly towards a religion😡😡

10. what are the consequences of not normalizing the images to 1/255 ([0,1] range)?

11. is there a way to rename 'My Drive' to something like 'my_drive' in google drive? Sometimes, the space cause trouble. I know we could rename sub folders in google drive. However I didn't find the way to rename the root 'My Drive'.

12. Another questions, should we save the training data in google drive and mount or copy them to colab? google drive is a cloud drive away from colab I guess. If save in google drive, the training would be slower or same same?

13. a third question is how to keep it training backstage. the training might take much time, the mount and even the colab runtime session might disconnected before training is finished. how to resolve this concern..

14. u been always helpful krish thank you so much

15. I got Tesla K80 for GPU, is that fine?

16. Dear krish, your theory explanation on deep learning helped me a lot. My pc is low configured, it dual core windows 7 64 bit. I know it's impossible to work with tensorflow with this configuration. Let me know is it possible to practice in cloud

17. Sir can you helpp.me i have image dataset in csv file and i have an image in this dataset so how can i fetch the image in loaded dataset??

18. I am unable to change the gpu to tesla T4..

19. 0:28 I've waited 25 years for this 🙂

20. Error is coming while I am performing model fir can you help me.out

21. Showing epoch 1/10 but then utbis showing failed to get convolution algorithm , because of cuDNN failed so try looking to see if a warning log message is printed above this error is coming how to solve sir

22. thanks

23. Getting this error
    UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.

24. Hello Sir,
    Can You please tell me How to save the model in Google Colab?

25. How to predict a test image other than that from dataset?

26. in this dataset, we have 2 folders one 'train' for testing and another 'valid' dir is for training ?? anyone is this right

27. Now this video is nothing but a gem.. Thank you Krish.. Just 1 question… I have seen in many datasets there is another folder called validation.. Why it's so and what's the use? Can you please explain or guide me to any of your video wish such a reference

28. Thanks, sir for such a detailed explanation, sir I'm trying to execute the code for the image dataset. but during fit a model I'm getting error after 1st epoch.
    InvalidArgumentError Traceback (most recent call last)
    
    <ipython-input-18-69229fe26ea3> in <module>()
    
    6 epochs=50,
    
    7 steps_per_epoch=len(training_set),
    
    —-> 8 validation_steps=len(test_set)
    
    9 )
    please help me to resolve this

29. The path of image should be on Google drive? What if i am working with jupyter and i decide the path in my local device its will work?

30. Can anyone please help me to find where did he put the code .

31. Can you please tell how to train gfp- gan ffhq – dataset

32. Sir I am getting graph execution error

33. Hi Krish,
    Thank you for your tutorials.
    I am a beginner, and I am wandering why didn't you use validation and test, both of the datasets to evaluate the model?
    thanks

34. Can you implement multioriented text detection using deep learning?

35. any solution? in jupyter notebook

    —-> 3 r = model.fit_generator(
    
    4 training_set,
    
    5 validation_data=test_set,
    
    6 epochs=10,
    
    7 steps_per_epoch=len(training_set),
    
    8 validation_steps=len(test_set)

36. any solution? in google collab
    InvalidArgumentError Traceback (most recent call last)
    
    <ipython-input-22-c27d8fba63ce> in <module>()
    
    6 epochs=10,
    
    7 steps_per_epoch=len(training_set),
    
    —-> 8 validation_steps=len(test_set)

37. HI Krish…. I need the concepts of Inception V3 Architecture..If already video is done can u please share the link?

38. Sir i have been following your tutorials. i need some little help. how i can run project files with connecting one code cell to another code cell. please help i am waiting for your response.

39. Sir i have been following your tutorials. i need some little help. how i can run project files with connecting one code cell to another code cell. please help i am waiting for your response.

40. Your code is nowhere to found on your git!

41. The code you are using is not available on your git

42. Can you please guide me on how to access the server through SSR, and how to train the deep learning model with the high-performance server with ssh and a webpage? i will be very thankful if you and anyone here guide me about this

43. sir , How can i add more layers?

44. ValueError: Asked to retrieve element 0, but the Sequence has length 0

45. ValueError: Asked to retrieve element 0, but the Sequence has length 0 …Can you fix this error kindly?

46. Nice tutorial sir .After training on colab ,can I download my model and use as pretrianed model ?

47. Man what if I have the Dataset not in direcotires but as variables in my coding sheet.
    ie: df_train

    Dude btw InceptionV3 how can that be helpful on leaf's datsets? I mean i know it is a powerful model that used many images, but srsly how that can help this kind dataset?

Comments are closed.