Impulse #1
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) 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 "model_unquant.tflite"
Configure model settings for optimal processing.
Model input
Input shape: (224, 224, 3)
How is your input scaled?
Input should be in RGB format (one value per pixel). If your model uses a different channel order, or is scaled differently, then select "Other".
Resize mode
Input data will be automatically resized to match the model input shape using this mode.
For best accuracy, upload pre-processed testing data.
Model output
Output shape: (10)
Output labels (10)
Enter labels for your model separated by ','.
On-device performance
Engine:
Check model behavior
Upload test data to ensure correct model settings and proper model processing. (Optional)
Upload an image
Upload an image to try out your model. The image will be automatically resized to
224x224 (RGB).
