Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
Digital Twin Journey: Computer Vision AI Model Enhancement with Dell Technologies Solutions & NVIDIA Omniverse
Introduction Business considerations Solution overview Partner overview Solution architecture overview Use case validation
Use case validation
3D simulations
Simple scene interaction with SimReady assets Complex scene interaction with Several SimReady assets
Synthetic data generation
Developing a Computer Vision AI object detection model with synthetic data
Training and validation Inferencing
Conclusions References

Developing a Computer Vision AI object detection model with synthetic data

Home > Workload Solutions > Computer Vision > White Papers > Digital Twin Journey: Computer Vision AI Model Enhancement with Dell Technologies Solutions & NVIDIA Omniverse > Developing a Computer Vision AI object detection model with synthetic data

Developing a Computer Vision AI object detection model with synthetic data

  • Training and validation

    We conducted training and validation with various numbers of synthetic images to categorize model performance. The following table shows the validation accuracy based on the number of synthetic images used in training.

    Table 6. Validation accuracy with synthetic images
    Number of Synthetic Images

    Validation Accuracy

    0 Pre-Trained Model Base Line 2%
    100 25%
    500 62%
    5000 83%