Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

Shape dimention problem

idata
Employee
431 Views

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

 

EXRARTA

 

Traceback (most recent call last):

 

File "/usr/local/bin/mvNCCompile", line 169, in

 

create_graph(args.network, args.image, args.inputnode, args.outputnode, args.outfile, args.nshaves, args.inputsize, args.weights, args.explicit_concat, args.ma2480, args.scheduler, args.new_parser, args)

 

File "/usr/local/bin/mvNCCompile", line 148, in create_graph

 

load_ret = load_network(args, parser, myriad_config)

 

File "/usr/local/bin/ncsdk/Controllers/Scheduler.py", line 100, in load_network

 

parse_ret = parse_tensor(arguments, myriad_conf)

 

File "/usr/local/bin/ncsdk/Controllers/TensorFlowParser.py", line 250, in parse_tensor

 

if None == shape_list[0]:

 

IndexError: list index out of range

 

What is this error ? Where should I do modification ?

0 Kudos
2 Replies
idata
Employee
253 Views

@punitvara Which model are you using? Looks like the TensorFlow parser is trying to access indexes of a tensor that doesn't exist. Can you provide a link to your model for debugging?

0 Kudos
idata
Employee
253 Views

Hi, I'm struggling with the same problem. In my case I was trying to compile the model from this reposirory provided in this intel blog post

 

with the following command: mvNCCheck retrained_graph.pb -s 12 -in=DecodeJpeg/contents -on=final_result

 

returning the same error

0 Kudos
Reply