Universal Robots PolyScope X User Manual page 40

13. Demo: Table Pick and Place
7. Once you annotate all the images in the training set, click Actions and Export Annotations.
8. Select Single file in COCO JSON format and click Export.
9. Save the exported file to Downloads.
10. Inside the /ros/data/datasets create folder rtdetr_active
11. Inside create "train" folder and copy images of the training set and downloaded coco json
file in here. Rename json file to coco_train.json
The training data consists of a combination of the JSON file and images.
1.
To prepare
the validation
set
2.
3.
4.
1.
To train the
model
2.
The training of the model can take anything from several minutes, depending on the total
number of images and labeled objects in each image.
User Manual
Repeat the above steps to create the validation set. Starting with uploading
remaining 20% of the images to MakeSense.ai
Make sure to use the same label as in the training set.
Create folder validation inside the rtdetr_active
Rename downloaded coco json file to coco_validation.json and copy it
together with the images from validation set in to the validation folder.
Train the model using GUI (you can restart it from run_ark.sh )
Use Train model in rtdetr_active column of the GUI.
40 AI Robotics Kit