Return types and error codes
Return codes for Edge Impulse functions.
Source: dsp/returntypes.h
EI_IMPULSE_ERROR
Value | Description |
---|---|
| Success |
| The shape of data does not match the shape of input layer. |
| Impulse execution is cancelled by user. |
| Error in TesnorFlow Lite inference engine |
| Error in processing portion of impulse |
| Failed to allocate memory in TensorFlow Lite arena, often caused by a lack of available heap memory. |
| Error in CubeAI inference engine (STM32) |
| Memory allocation failed. Could be caused by a fragmented heap. Try to increase heap size. |
| This function is only supported for impulses with an image input. |
| The chosen inference engine (e.g. in Studio) is incapable of running this impulse. |
| Out of memory. Could be caused by a fragmented heap. Try to increase heap size. |
| Input tensor was null |
| Output tensor was null |
| Score tensor is null (for SSD Object Detection models). |
| Label tensor is null (for SSD Object Detection models). |
| TensorRT (NVIDIA) initialization failed. |
| DRP-AI (Renesas) initialization failed. |
| DRP-AI (Renesas) runtime failed. |
| The model is deprecated and cannot be used. You should re-export the impulse from Studio. |
| The last layer is not available in the model. |
| Error during inference. |
| Error in Akida inference engine (BrainChip) |
| The shape of data does not match the shape of input layer. |
| Error in ONNX inference engine |
| Error in Memryx inference engine |
Last updated