@fawen ValueError: operands could not be broadcast together with shapes (1,3,80,80,0) (1,3,80,80,2)
[495133] Failed to execute script 'pegasus' due to unhandled exception!

@whycanservice 您好，这个问题是参数因为没有写对吗

@whycanservice yolov5$ pegasus import onnx --model yolov5n-sim.onnx --output-data yolov5n-sim.data --output-model yolov5n-sim.json --outputs "350 498 646"

@whycanservice https://v853.docs.aw-ol.com/npu/npu_yolov5/

@whycanservice pegasus import onnx --model yolov5n-sim.onnx --output-data yolov5n-sim.data --output-model yolov5n-sim.json --outputs "350 498 646"

......
W Call onnx.optimizer.optimize fail, skip optimize
I Current ONNX Model use ir_version 8 opset_version 17
Traceback (most recent call last):
File "pegasus.py", line 131, in <module>
File "pegasus.py", line 112, in main
File "acuitylib/app/importer/commands.py", line 248, in execute
File "acuitylib/vsi_nn.py", line 125, in load_onnx
File "acuitylib/app/importer/import_onnx.py", line 117, in run
File "acuitylib/converter/onnx/convert_onnx.py", line 62, in init
File "acuitylib/converter/onnx/convert_onnx.py", line 90, in __build_specified_subgraph
File "acuitylib/converter/onnx/onnx_util.py", line 400, in build_subgraph
File "acuitylib/converter/onnx/onnx_util.py", line 400, in <listcomp>
KeyError: '350'
[******] Failed to execute script 'pegasus' due to unhandled exception!

Failed to execute script 'pegasus' due to unhandled exception!