If you get an error like below while running your app:
[error] [infer_utils.cpp:41] %s [error] [gxf_wrapper.cpp:68] Exception occurred for operator: 'segmentation_inference' - Error in Inference Operator, Sub-module->Tick, Inference execution, Message->Error in Inference Operator, Sub-module->Tick, Data extraction [error] [entity_executor.cpp:529] Failed to tick codelet segmentation_inference in entity: segmentation_inference code: GXF_FAILURE [warning] [greedy_scheduler.cpp:242] Error while executing entity 43 named 'segmentation_inference': GXF_FAILURE [info] [greedy_scheduler.cpp:398] Scheduler finished. [error] [program.cpp:556] wait failed. Deactivating... [error] [runtime.cpp:1408] Graph wait failed with error: GXF_FAILURE [warning] [gxf_executor.cpp:1775] GXF call GxfGraphWait(context) in line 1775 of file /workspace/holoscan-sdk/src/core/executors/gxf/gxf_executor.cpp failed with 'GXF_FAILURE' (1) [error] [gxf_executor.cpp:1779] GxfGraphWait Error: GXF_FAILURE Traceback (most recent call last): File "tool_segmentation.py", line 193, in <module> app.run() RuntimeError: Failure: Failed to wait for graph to complete
This is likely due to the InferenceOp’s specification of the input tensor name (whether in
in_tensor_names) not matching the output tensor name of the upstream operator.