Computer vision models
The YOLO, SAM and OmniParser methods require simultaneously prepared constraints, a compatible model file, and the selected model in the method settings.
General procedure
- Check the machine learning component on the dependencies page.
- Open the settings of the models of the selected family.
- Download a supported model or provide a trusted local file.
- Select the active model and perform a boot check.
- Run the method on a test image before working on an important project.
Model families
| Family | Purpose | Features |
|---|---|---|
| YOLO | Detection, segmentation and pose estimation - depending on the selected model. | The model problem type must match the method. |
| SAM | Segment by point, frame, or other cue. | Different options require different files and resources. |
| OmniParser | Search and description of interface elements. | A complete process may require multiple consistent models. |
Downloads and privacy
Loading of the model begins only after user action. The model server receives the normal technical data of an HTTPS request, but Screph does not send it the design, markup, or source images. Once loaded, processing is done locally.
For a closed network, you can use pre-prepared local files. Load models only from trusted sources: the model file may contain data that is processed by software libraries when opened.
File verification
If a checksum is published for a model, Screph can compare it with a local file. A match confirms the integrity of the file, but does not guarantee the quality of the model or suitability for a particular task.
Typical reasons for unavailability
- Machine learning dependencies are not prepared.
- The file is missing, damaged, or does not match the selected family.
- The active model is not selected in the settings.
- There is not enough memory or free space.
Preparing components is described in the "Dependencies and Updates" section.