Choose a Model Deployment Path
reCamera Pro supports deploying custom AI models for object detection, classification, and other tasks. This page helps you choose the right path based on your model format and workflow.
Three deployment paths
| Path | When to use | Skill level |
|---|---|---|
| Upload a pre-trained RKNN model | You already have an RKNN model file (.rknn) | Beginner |
| Convert ONNX to RKNN via SenseCraft | You have an ONNX model and want cloud-based conversion | Beginner–Intermediate |
| Convert ONNX to RKNN via RKNN-Toolkit2 | You want full control over quantization (INT8/FP16) and calibration | Intermediate–Advanced |
Path 1: Upload a pre-trained RKNN model
If you already have a .rknn model file, upload it directly via the Web UI.
→ Upload and Configure an RKNN Model
Path 2: SenseCraft cloud conversion
The SenseCraft platform converts ONNX models to RKNN format in the cloud, with optional quantization. No local tooling required.
→ SenseCraft ONNX-to-RKNN Conversion
Path 3: RKNN-Toolkit2 local conversion
For full control over quantization parameters, calibration datasets, and model optimization, use RKNN-Toolkit2 on your PC.
After deploying
Once your model is on the device:
- Configure Detection — set classes, thresholds, and inference frequency
- Validate Model Performance — check FPS, accuracy, and resource usage
- Model Compatibility — supported operators and quantization formats
Related pages
- Upload and Configure an RKNN Model
- SenseCraft ONNX-to-RKNN Conversion
- RKNN-Toolkit2 Conversion
- Validate Model Performance
Tech Support & Product Discussion
Thank you for choosing our products! We are here to provide you with different support to ensure that your experience with our products is as smooth as possible. We offer several communication channels to cater to different preferences and needs.