like to apply kmeans segmentation to images
but i got this exact question:
-How to determine the number of classes in images segmentation
And this answer:
-The determination of the "right" number of clusters is something you will have to decide based on your application. We will not be able to help with that - especially without seeing an image.
Is there an unsupervised algorithm for this that guesses how many clusters should it have?
In unsupervised labeling knn, u calculate similarity of your training data and draw the chart, now you can visually see how many clusters are existed
Man try by changing the data types, floats to float32, ints to unsigned, text to categorical those that fit to be so
Обсуждают сегодня