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

mvNCCompile throws :ValueError: 'net_output' is not in list

Hello everyone

 

     

  • I run the following command for compiling a graph:

     

    "mvNCCompile pose_deploy_linevec_faster_4_stages.prototxt -w pose_iter_160000.caffemodel -s 12 -is 100 100 -o OpenPoseGraph"
  •  

  • The .prototxt can be fonud here:

     

    https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/models/pose/mpi/pose_deploy_lin...
  •  

  • The .caffemodel can be downloaded using this link:

     

    http://posefs1.perception.cs.cmu.edu/OpenPose/models/pose/mpi/pose_iter_160000.caffemodel
  •  

  • output is the following:

     

    /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/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 88 from C header, got 96 from PyObject

     

    return f(*args, **kwds)

     

    /usr/local/bin/ncsdk/Controllers/Parsers/TensorFlowParser/Convolution.py:47: 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
  •  

 

Traceback (most recent call last):

 

File "/usr/local/bin/mvNCCompile", line 208, in

 

args.old_parser, args.cpp, args)

 

File "/usr/local/bin/mvNCCompile", line 186, in create_graph

 

load_ret = load_network(args, parser, myriad_config)

 

File "/usr/local/bin/ncsdk/Controllers/Scheduler.py", line 83, in load_network

 

input_data, expected_result = p.calculateReference(arguments)

 

File "/usr/local/bin/ncsdk/Controllers/Parsers/Caffe.py", line 209, in calculateReference

 

output = self.net.forward(start=first_layer, end=out_label)

 

File "/opt/movidius/caffe/python/caffe/pycaffe.py", line 105, in _Net_forward

 

end_ind = list(self._layer_names).index(end)

 

ValueError: 'net_output' is not in list

 

     

  • When looking in the .prototxt file, the last described node looks like this:

     

    layer {

     

    name: "concat_stage7"

     

    type: "Concat"

     

    bottom: "Mconv7_stage4_L2"

     

    bottom: "Mconv7_stage4_L1"

     

    top: "net_output"

     

    concat_param {

     

    axis: 1

     

    }

     

    }
  •  

 

so, a "net_output" exists.

 

Any idea on how to solve this issue is very much appreciated.

 

All the best,

 

Bastian
Tags (1)
0 Kudos
1 Reply
idata
Community Manager
91 Views

Hi @bastiank

 

Could you try to set the top parameter to the same name of the layer (See below)?

 

layer { name: "concat_stage7" type: "Concat" bottom: "Mconv7_stage4_L2" bottom: "Mconv7_stage4_L1" top: "concat_stage7" concat_param { axis: 1 } }

 

Regards,

 

Jesus
Reply