Feature Request: FOMO transparent background auto filled

As I get better at training FOMO. One of the tricks for me has been to increase the amount of backgrounds behind the bounding boxes. It occurs to me that if I set bounding boxes to objects on a translucent background image, it would be very useful if edgeimpusle filled in the background with multiple different colors or random backgrounds. Presently I don’t think edgeimpulse allows images with translucent background.

Actually changing the background can be done fairly easily manually by.

  1. removing all items from the test set to the training set
  2. load into the test set an image of objects with a continuous background color like white
  3. set your bounding boxes
  4. make sure this is the only image in the test set
  5. export your data, backup the testing set folder.
  6. in the testing set folder, (has the image and bounding box JSON data) change the background color, save the image (don’t change file names).
  7. upload the image and bounding box info to the test set
  8. check it arrived and repeat
  9. when all images with new backgrounds have been uploaded move all images to training set
  10. rebalance dataset.
  11. retrain
1 Like

Hi @Rocksetta,

Good find :slight_smile: Something that I like to do is write a Google Colab script that will perform data augmentation automatically so that I can just send it a few samples and it will mix in different backgrounds (I did this for keyword spotting, but I have to imagine it’s possible for images). You can then use the EI uploader to automatically send everything to your Studio project.

1 Like