TF输入为迭代器时出现问题

[复制链接] · 发表于 2019-5-29 15:15:59

尝试将shufflenet-V2 tf通过ckpt转pb转rknn的方式进行推理，通过Netron看到输入为IteratorGetNext，输出为Softmax。原始模型的链接为：
https://github.com/TropComplique/shufflenet-v2-tensorflow
在载入pb时报以下错误，怀疑是输入为迭代器出现的问题，请问该种情况如何解决？

--> Loading model
Catch exception when loading tensorflow model: ./shufflenet_v2_1.0x/shufflenet_v2_1.0x.pb!
Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/importer.py", line 426, in import_graph_def
graph._c_graph, serialized, options)  # pylint: disable=protected-access
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input 0 of node IteratorGetNext was passed float from Iterator_out_0_placeholder:0 incompatible with expected resource.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/rknn/api/rknn.py", line 50, in load_tensorflow
std_values=std_values)
  File "rknn/api/redirect_stdout.py", line 67, in rknn.api.redirect_stdout.redirect_stdout.func_wrapper
  File "rknn/api/redirect_stdout.py", line 68, in rknn.api.redirect_stdout.redirect_stdout.func_wrapper
  File "rknn/api/rknn_base.py", line 139, in rknn.api.rknn_base.RKNNBase.load_tensorflow
  File "rknn/base/rknnlib/converter/convert_tf.py", line 432, in rknn.base.rknnlib.converter.convert_tf.convert_tf.pre_process
  File "rknn/base/rknnlib/converter/tensorflowloader.py", line 102, in rknn.base.rknnlib.converter.tensorflowloader.TF_Graph_Preprocess.pre_proces
  File "rknn/base/rknnlib/converter/tensorflowloader.py", line 621, in rknn.base.rknnlib.converter.tensorflowloader.TF_Graph_Preprocess.calc_2_const
  File "rknn/base/rknnlib/converter/tf_util.py", line 375, in rknn.base.rknnlib.converter.tf_util.TFProto_Util.query_tensor
  File "rknn/base/rknnlib/converter/tf_util.py", line 376, in rknn.base.rknnlib.converter.tf_util.TFProto_Util.query_tensor
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/importer.py", line 430, in import_graph_def
raise ValueError(str(e))
ValueError: Input 0 of node IteratorGetNext was passed float from Iterator_out_0_placeholder:0 incompatible with expected resource.

Load shufflenet_v2_1.0x failed! Ret = -1