正在运行最新的WinMLRunning，但出现错误：
没有为op Add找到合适的内核定义（节点InceptionV1 / InceptionV1 / Conv2d_1a_7x7 / BatchNorm / FusedBatchNorm）
我使用VS或mmdnn将自定义推理冻结的Inception模型转换为ONNX。从头开始编写新的Win32 WinML桌面应用程序时出现类似错误。
OS: 17758 insider preview SDK : 17754 insider preview VS: 15.8.4 WinML Runner GPU: Intel(R) UHD Graphics 620 ================================================================= Name: tf2onnx Author: tf2onnx Version: 9223372036854775807 Domain: Description: Path: test3.onnx Support FP16: false Input Feature Info: Name: input:0 Feature Kind: Float Output Feature Info: Name: InceptionV1/Logits/Predictions/Reshape_1:0 Feature Kind: Float ================================================================= Loading model...[SUCCESS] Creating session [FAILED] No suitable kernel definition found for op Add (node InceptionV1/InceptionV1/Conv2d_1a_7x7/BatchNorm/FusedBatchNorm) ================================================================= Name: tf2onnx Author: tf2onnx Version: 9223372036854775807 Domain: Description: Path: test3.onnx Support FP16: false Input Feature Info: Name: input:0 Feature Kind: Float Output Feature Info: Name: InceptionV1/Logits/Predictions/Reshape_1:0 Feature Kind: Float ================================================================= Loading model...[SUCCESS] Creating session [FAILED] No suitable kernel definition found for op Add (node InceptionV1/InceptionV1/Conv2d_1a_7x7/BatchNorm/FusedBatchNorm)
答案 0 :(得分：3)
请确保您的操作员版本是最新的。要检查版本，请使用Netron打开模型，单击输入节点并检查Imports字段。
我们希望： ai.onnx v7 用于ONNX Operator Set 7，这是Windows Machine Learning API支持的最低版本。
尝试使用tf2onnx转换工具从tensorflow转换。您可能还需要更新ONNX python软件包。我们支持 ONNX 1.2.2或更高版本：https://github.com/onnx/tensorflow-onnx
此问题已在此处解决：https://github.com/Microsoft/Windows-Machine-Learning/issues/50