Community
cancel
Showing results for 
Search instead for 
Did you mean: 
idata
Community Manager
386 Views

Conversion of tensorflow graph is successful but the result with movidius graph is strange

I have a tensorflow model at https://drive.google.com/file/d/13H9d4m59YAawSVzu5ERqwKo3U7QAVsOR/view?usp=sharing. Input node is "input", output node is "output".

 

Here is the log

 

/usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead.

 

from numpy.testing.decorators import setastest

 

/usr/local/bin/ncsdk/Controllers/Parsers/TensorFlowParser/Convolution.py:44: SyntaxWarning: assertion is always true, perhaps remove parentheses?

 

assert(False, "Layer type not supported by Convolution: " + obj.type)

 

mvNCCompile v02.00, Copyright @ Intel Corporation 2017

 

/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/tf_inspect.py:45: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead shape: (1, 224, 224, 3) res.shape: (1, 1, 1, 11) TensorFlow output shape: (1, 1, 11) /usr/local/bin/ncsdk/Controllers/FileIO.py:65: UserWarning: You are using a large type. Consider reducing your data sizes for best performance Blob generated

 

My output node is a concatenated result of:

 

output1 = tf.reshape(endpoints['movidius_endpoints1'], shape=(1,1,1,9)) output2 = tf.reshape(endpoints['movidius_endpoints1'], shape=(1,1,1,2)) output = tf.concat([output1, output2], -1, name='concate') output = tf.identity(output, name='output')

 

However, when i run the inference on movidius, what i get is just a tensor of shape (2,)

 

Please help to take a look

0 Kudos
0 Replies
Reply