ReduceSum with operands type (SIGNED, 32 bit, C Size: 32 bits) is not supported

[XBao]

Hello!

I'm getting the error when I analyze an ONNX model using  ST Edge AI Developer Cloud : NOT IMPLEMENTED: ReduceSum with operands type (SIGNED, 32 bit, C Size: 32 bits) is not supported. I have tried to convert the float32 data to float16, but it is not supported (TOOL ERROR: Unsupported elem type FLOAT16 for tensor Cast_1_output_0). The model was attached below. The model was generated in Pytorch, and the MCU was STM32H753VIT6. I'd like to know if anyone has had this problem and how it was resolved?

I would appreciate it if anyone could help to figure out what could be the problem. I attach my model below in case someone can help me. Thanks in advance. Regards!

[Julian E.]

Hello @XBao ,

Sorry for the late answer.

In you case, even if you are working with a float32 model, the ReduceSum layer is taking an int32 input.

ReduceSum only support float32 at the moment, so you need to convert to the input to the ReduceSum layer to float32.

I don't exactly know what you model do, but I would imagine that this layer is used on indexes, that are in this case int32.

For float16, we don't support it, which cause an error.

Have a good day,

Julian