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

[idata]

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_linevec_faster_4_stages.prototxt

• 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 PyObjectreturn 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

[idata]

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