Impulse #2
Upload pretrained model - Step 1: Upload a model
1. Upload your trained model
Upload a
TensorFlow SavedModel (saved_model.zip),
ONNX model (.onnx),
TensorFlow Lite model (.tflite),
LGBM model (.txt),
XGBoost model (.json),
NGBoost model (ngboost.pkl) or
pickle model (.pkl)
to get started.
2. Model performance
Do you want performance characteristics (latency, RAM and ROM) for a specific device?
Step 2: Process "smoke_detection_model (2).tflite"
Configure model settings for optimal processing.
Model input
Input shape: (12)
Model output
Output shape: (2)
Output labels (2)
Enter labels for your model separated by ','.
On-device performance
MCUs
| EON Compiler | TFLite | ||||
|---|---|---|---|---|---|
| Device | Latency | RAM | ROM | RAM | ROM |
| Low-end MCU | 552 ms. | 5.1K | 697.4K | 9.1K +4.0K | 719.2K +21.8K |
| High-end MCU | 6 ms. | 5.6K | 700.0K | 9.7K +4.1K | 728.2K +28.2K |
| + AI accelerator | 6 ms. | 5.6K | 700.0K | 9.7K +4.1K | 728.2K +28.2K |
Microprocessors
| Device | Latency | Model size |
|---|---|---|
| CPU | 1 ms. | 689.7K |
| GPU or accelerator | 1 ms. | 689.7K |
Check model behavior
Upload test data to ensure correct model settings and proper model processing. (Optional)
Enter features
Enter 12 input features for this model, separated by ','.
