GroundingDINO模型onnx转bmodel时，报keyError: 'operand /Constant_2_output_0 not found'

[jiajia1417]

报下面这个错误

Traceback (most recent call last):
  File "/workspace/tpu-mlir/python/tools/model_transform.py", line 442, in <module>
    tool.model_transform(args.mlir, args.add_postprocess, args.patterns_count)
  File "/workspace/tpu-mlir/python/tools/model_transform.py", line 63, in model_transform
    self.converter.generate_mlir(mlir_origin)
  File "/workspace/tpu-mlir/python/transform/OnnxConverter.py", line 739, in generate_mlir
    self.onnxop_factory.get(n.op_type, lambda x: NoneAndRaise(x))(n)
  File "/workspace/tpu-mlir/python/transform/OnnxConverter.py", line 250, in <lambda>
    "ReduceMax": lambda node: self.convert_reduce_op(node),
  File "/workspace/tpu-mlir/python/transform/OnnxConverter.py", line 1909, in convert_reduce_op
    op = self.getOperand(onnx_node.inputs[0])
  File "/workspace/tpu-mlir/python/transform/BaseConverter.py", line 54, in getOperand
    raise KeyError("operand {} not found".format(name))
KeyError: 'operand /Constant_2_output_0 not found'

但是我检查onnx节点时，发现是有/Constant_2_output_0这个输出节点的
用下面代码打印onnx节点

for idx, node in enumerate(model.graph.node):
    print(f"\n节点 {idx + 1}:")
    print(f"  名称: {node.name}")
    print(f"  类型: {node.op_type}")
    print(f"  输入: {node.input}")
    print(f"  输出: {node.output}")

输出结果

节点 15810:
  名称: /class_embed.0/Constant_2
  类型: Constant
  输入: []
  输出: ['/class_embed.0/Constant_2_output_0'] 

可以看到是有Constant_2_output_0这个键的，但是还是报了 KeyError: 'operand /Constant_2_output_0 not found 这个错误