tensorflow转换模型遇到的问题

Question

tensorflow.lite.python.convert_phase.ConverterError: C:\Users\86130\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\layers\normalization\batch_normalization.py:660:0: error: 'tf.FusedBatchNormV3' op is neither a custom op nor a flex op
<unknown>:0: note: loc(fused["StatefulPartitionedCall:", "StatefulPartitionedCall"]): called from
C:\Users\86130\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\layers\normalization\batch_normalization.py:660:0: note: Error code: ERROR_NEEDS_FLEX_OPS
C:\Users\86130\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\keras\layers\normalization\batch_normalization.py:660:0: error: 'tf.FusedBatchNormV3' op is neither a custom op nor a flex op

哪位知道这个问题是因为什么

Answer 1

• 这篇博客也许可以解决你的问题👉 ：Tensorflow用自己的数据集训练模型