I am currently studying a machine learning course and now we are asked (each student) to find an image dataset to work on for the course project. I am new to ML and it has been a week and I am trying to find a good dataset (easy and not complicated) to work on, but all I found are ones for tough topics such as lung cancer detection, plant disease detection,... etc. So please someone help me to locate a good one for a beginner.

  • $\begingroup$ This is a a classy and easy one kaggle.com/c/dogs-vs-cats assuming that others, such as MNIST, have been covered in your lectures already. $\endgroup$
    – Jonathan
    Commented Jan 16, 2021 at 8:48
  • $\begingroup$ @Sammy Many thanks for your help. But can I have a dataset a little bit harder than this? $\endgroup$
    – John adams
    Commented Jan 16, 2021 at 8:57
  • $\begingroup$ Well, it's a bit of a guessing game. Google street view house numbers is another relatively easy one. Can you be more specific what you are looking for? For example: type of task, dataset size, etc. $\endgroup$
    – Jonathan
    Commented Jan 16, 2021 at 9:44
  • $\begingroup$ @Sammy thank you very much for your help . Is this the dataset : ufldl.stanford.edu/housenumbers ? Can you further explain the task to achieve ( like what is exactly the output of ML model ) ? $\endgroup$
    – John adams
    Commented Jan 16, 2021 at 9:54
  • $\begingroup$ Yes, it is. Have a look at the paper linked on the website. You'll find a description of a classification task applied to it. $\endgroup$
    – Jonathan
    Commented Jan 16, 2021 at 14:06


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.