discuss-gnuradio
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Discuss-gnuradio] Error while loading graph to GR-inspector AMC blo


From: Jonas Manthey
Subject: Re: [Discuss-gnuradio] Error while loading graph to GR-inspector AMC block
Date: Wed, 29 May 2019 07:22:19 +0000

Hi,

 

For more complex applications, especially using external libraries, I’d recommend to switch to “pure” python and a proper IDE like PyCharm instead of gnuradio-companion. This will allow you to set break points and debug your application, because to me it seems this is a tensorflow issue and not GNURadio related.

You can always use your “top_block.py” as a starting point for the pure python application.

 

Cheers,

Jonas

 

From: Discuss-gnuradio [mailto:discuss-gnuradio-bounces+address@hidden On Behalf Of Daniel Andres Palacios
Sent: Mittwoch, 29. Mai 2019 02:17
To: address@hidden
Subject: [Discuss-gnuradio] Error while loading graph to GR-inspector AMC block

 

Hi all.I'm getting this error when trying to use the AMC block. I generated the graph with tensorflow 0.12.1

 

 

Loading: "/home/dandrspc/default/src/gr-inspector/examples/amc_cnn.grc"

>>> Done

Generating: '/home/dandrspc/default/src/gr-inspector/examples/top_block.py'

Executing: /usr/bin/python2 -u /home/dandrspc/default/src/gr-inspector/examples/
top_block.py

Traceback (most recent call last):
  File "/home/dandrspc/default/src/gr-inspector/examples/top_block.py", line 142
, in <module>
    main()
  File "/home/dandrspc/default/src/gr-inspector/examples/top_block.py", line 130
, in main
    tb = top_block_cls()
  File "/home/dandrspc/default/src/gr-inspector/examples/top_block.py", line 76,
 in __init__
    self.inspector_tfmodel_vcf_0 = inspector.tfmodel_vcf("complex64",128,'/home/
dandrspc/Documentos/signal intelligence/examples-master/modulation_recognition/c
nn_/00000002',(),0)
  File "/home/dandrspc/default/lib/python2.7/dist-packages/inspector/tfmodel_vcf
.py", line 64, in __init__
    sess, inp, out,classes = self.load_graph(graphfile)
  File "/home/dandrspc/default/lib/python2.7/dist-packages/inspector/tfmodel_vcf
.py", line 80, in load_graph
    output_graph_path)
  File "/home/dandrspc/.local/lib/python2.7/site-packages/tensorflow/contrib/ses
sion_bundle/session_bundle.py", line 86, in load_session_bundle_from_path
    "Expected exactly one serving GraphDef in : %s" % meta_graph_def)
RuntimeError: Expected exactly one serving GraphDef in : meta_info_def {
  stripped_op_list {
    op {
      name: "Add"
      input_arg {
        name: "x"
        type_attr: "T"
      }
      input_arg {
        name: "y"
        type_attr: "T"
      }


--

Daniel Andrés Palacios Carabalí

Student of Telemathics engineering

Icesi University- Cali, Colombia

===========================

Estudiante de Ingeniería Telemática

Universidad Icesi. - Cali, Colombia


reply via email to

[Prev in Thread] Current Thread [Next in Thread]