Tool/software:
Hello,
I'am trying to implement a custom operator "Equal" to but I have a probelm with the input.
My model is an onnx model with 1 variable input, 1 constant input, 1 output and 1 layer which is Equal operator. (as in the screenshot)
When I try to copile my model I have this error:
[TIDL Import] [PARSER] UNSUPPORTED: All the input tensor dimensions has to be greater then zero. For tensor , id 1 - Dim 3 is -1 -- [tidl_import_common_model_check.cpp, 2309] [TIDL Import] ERROR: Invalid input tensor dimension, aborting -- [tidl_import_core.cpp, 2653] [TIDL Import] ERROR: Network Optimization failed - Failed in function: TIDL_runtimesOptimizeNet -- [tidl_runtimes_import_common.cpp, 1287] [TIDL Import] [PARSER] ERROR: - Failed in function: TIDL_computeImportFunc -- [tidl_onnxRtImport_EP.cpp, 2379]
I figured that the constant input si causing this error but I don't know how to resolve it.
Can you please help me?
Thank you.
