When I tried running the grade required cell for the function split_data() in Google Colab I waited 20 minutes but it was still working. I tried switching to standard runtime type from GPU but no improvement…
I dont think I have used inappropriate inputs. The one issue I can see is that I used a for loop to iterate over the files, but I don’t see a way to solve it without using one
If you can’t figure out, no issues. Send me your notebook via dm such that I can check where it went wrong. By clicking on the profile picture, you will see an option to message. There you can attach your notebook. Then we can discuss the issues here.
I have gone through your snippet.
There are several issues.
Logic is not correct for this part : All images should be checked before the copy, so if they have a zero file length, they will be omitted from the copying process.
Next,
At first , You need to find training and testing length.
Then shuffle.
Then find training set and testing set.
Longer training time can be encountered if one has not got the dataset codes as per the requirement. Also if there is any issue with the model algorithm. One needs to understand even if ones codes are correct, one can still encounter issue based on what one choose for convolution layer, batch size, learning rate and other parameters.
Kindly share your notebook via personal DM. I sincerely suggest you to create a new post, so there is a better log about what you encountered, it is not necessary that reason behind the issue might or might not be same.
He hasn’t responded since then in community. But his particular issue was solved with these and I know since I had his notebook :
Try these.
If these doesn’t help, create a separate post as @Deepti_Prasad has said, she will guide you there. There can be some different issue that will have a different solution.