I have been using Mask-RCNN for work. I have to do custom object detection. For this, I have labeled all my images using polygon in the given image. I have 50 images and hence I have 50 annotations.json files. But according to the information given on the Mask RCNN Github Repo, we need only one annotation JSON file.
So my question is:
How to change the export_boxes and load_mask functions given in the code to accommodate my problem? If so, how do I do that? or should I merge all the JSON files into one? If I go ahead with the merging, would that have the correct formatting?
Pls help me out.
regards,
Saqib
Here you can find answer, but be careful with folders specified in the script.
Here better change save folder for masks to save your image data (otherwise your image data will be replaced)
and there might be some problem with masks if you have different image_size/mask_size for initial data
https://towardsdatascience.com/generating-image-segmentation-masks-the-easy-way-dd4d3656dbd1
- Badges
- Science topic
- Similar topics
- Organizational Psychology
- Training