Timeline for Why doesn't my image classification network get better with training?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 18, 2019 at 21:52 | answer | added | pr3sidentspence | timeline score: 1 | |
| Mar 18, 2019 at 16:18 | comment | added | pr3sidentspence | I forgot that I already did that, re: ImageGenerator(). :\ | |
| Mar 18, 2019 at 14:47 | comment | added | pr3sidentspence | Thanks @OliverMason, I will try that. I was also thinking that maybe I need to make sure the ImageGenerator() isn't cropping the image such that the stamp area is missing. | |
| Mar 18, 2019 at 9:30 | comment | added | Oliver Mason | Machine learning unfortunately doesn't necessarily get better with more training data. If the classes in your problem are not clearly separable for the algorithm, then no amount of data will improve it. One issue could be that the classes are unbalanced; perhaps try to use fewer 'no-stamp' images. Or investigate pre-processing them, eg to amplify colours or other features, so that the classifier can pick them up better. | |
| Mar 18, 2019 at 2:30 | review | First posts | |||
| Mar 18, 2019 at 16:02 | |||||
| Mar 18, 2019 at 2:26 | history | asked | pr3sidentspence | CC BY-SA 4.0 |