Hi, I saw that the hard_sigmoid operator is supported in the document “Neural Network Layer and Operation Support Guide (02)(ref.v1.17-20200623).pdf” in aml_npu_sdk6.4.4.3, but I didn’t find it from caffe, tensorflow, tflite , Onnx, darknet and keras model conversion corresponding operators, I tried to use the onnx model conversion, an error was reported, is there any way to convert the hard_sigmoid operator?
I Try match HardSigmoid_HardSigmoid_2:out0
W Not match tensor HardSigmoid_HardSigmoid_2:out0
Traceback (most recent call last):
File "convertonnx.py", line 56, in <module>
File "convertonnx.py", line 45, in main
File "acuitylib/vsi_nn.py", line 139, in load_onnx
File "acuitylib/app/importer/import_onnx.py", line 124, in run
File "acuitylib/converter/convert_onnx.py", line 953, in match_paragraph_and_param
File "acuitylib/converter/convert_onnx.py", line 856, in _onnx_push_ready_tensor
TypeError: 'NoneType' object is not iterable
[1349490] Failed to execute script convertonnx