I use mtcnn to detect face, and followed the ncappzoo(https://github.com/movidius/ncappzoo/tree/master/tensorflow/MTCNN "https://github.com/movidius/ncappzoo/tree/master/tensorflow/MTCNN ") , but when using mvNCCheck , the accuracy is very low, so I use tensorflow1.2 to finetune the model , and then compile the new model. Now when I compile the new model , there is a bug as follows:
mvNCCheck v02.00, Copyright @ Movidius Ltd 2016
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py:766: DeprecationWarning: builtin type EagerTensor has no module attribute
EagerTensor = c_api.TFE_Py_InitEagerTensor(_EagerTensorBase)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/tf_inspect.py:45: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
if d.decorator_argspec is not None), _inspect.getargspec(target))
WARNING:tensorflow:The saved meta_graph is possibly from an older release:
'model_variables' collection should be of type 'byte_list', but instead is of type 'node_list'.
[Error 5] Toolkit Error: Stage Details Not Supported: Greater
The model - network layers /network layers name… are all same with the model before I fine tuned, so I don't know what's wrong with the "mvNCCompile" operation…
