error: Lowering tensor list ops is failed. Please consider using Select TF ops and disabling `_experimental_lower_tensor_list_ops` flag in the TFLite converter object. For example, converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]\n converter._experimental_lower_tensor_list_ops = False
Traceback (most recent call last):
File "C:\Users\panda\PycharmProjects\nlp\c.py", line 126, in <module>
binary_tflite_model = converter.convert()
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\lite.py", line 930, in wrapper
return self._convert_and_export_metrics(convert_func, *args, **kwargs)
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\lite.py", line 908, in _convert_and_export_metrics
result = convert_func(self, *args, **kwargs)
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\lite.py", line 1339, in convert
saved_model_convert_result = self._convert_as_saved_model()
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\lite.py", line 1322, in _convert_as_saved_model
self).convert(graph_def, input_tensors, output_tensors)
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\lite.py", line 1132, in convert
result = _convert_graphdef(
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\convert_phase.py", line 212, in wrapper
raise converter_error from None # Re-throws the exception.
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\convert_phase.py", line 205, in wrapper
return func(*args, **kwargs)
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\convert.py", line 794, in convert_graphdef
data = convert(
File "C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\lite\python\convert.py", line 311, in convert
raise converter_error
tensorflow.lite.python.convert_phase.ConverterError: C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\python\saved_model\save.py:1268:0: error: 'tf.TensorListReserve' op requires element_shape to be static during TF Lite transformation pass
<unknown>:0: note: loc(fused["StatefulPartitionedCall:", "StatefulPartitionedCall"]): called from
C:\Users\panda\.conda\envs\tf310\lib\site-packages\tensorflow\python\saved_model\save.py:1268:0: error: failed to legalize operation 'tf.TensorListReserve' that was explicitly marked illegal
<unknown>:0: note: loc(fused["StatefulPartitionedCall:", "StatefulPartitionedCall"]): called from
<unknown>:0: error: Lowering tensor list ops is failed. Please consider using Select TF ops and disabling `_experimental_lower_tensor_list_ops` flag in the TFLite converter object. For example, converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]\n converter._experimental_lower_tensor_list_ops = False
博客可能围绕TensorFlow与Android展开，TensorFlow是重要的机器学习框架，在人工智能领域应用广泛，而Android是主流移动操作系统。二者结合或可实现智能移动应用开发等信息技术相关内容。
扫一扫
3055
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
