Forums - After pruning disconnected nodes, this model is empty

2 posts / 0 new
or Register
Last post
After pruning disconnected nodes, this model is empty
shanghui_eml
Join Date: 13 Oct 21
Posts: 6
Posted: Wed, 2021-10-13 23:36
Top

Hi, 

I am try to convert my SSD .pb model to .dlc, but this error occured. 

2021-10-14 14:30:40,243 - 193 - WARNING - WARNING_TF_LAYER_NOT_CONSUMED: Layer (Cast) of type (Cast) is not consumed by converter.
2021-10-14 14:30:40,248 - 193 - WARNING - Output node detection_scores, specified via command line, does not exist in graph.
2021-10-14 14:30:40,248 - 193 - WARNING - Output node detection_classes, specified via command line, does not exist in graph.
2021-10-14 14:30:40,248 - 193 - WARNING - Output node detection_boxes, specified via command line, does not exist in graph.
2021-10-14 14:30:40,249 - 183 - ERROR - Conversion FAILED!
Traceback (most recent call last):
  File "/home/snpe/snpe-1.52.0.2724/bin/x86_64-linux-clang/snpe-tensorflow-to-dlc", line 71, in <module>
    main()
  File "/home/snpe/snpe-1.52.0.2724/bin/x86_64-linux-clang/snpe-tensorflow-to-dlc", line 67, in main
    raise e
  File "/home/snpe/snpe-1.52.0.2724/bin/x86_64-linux-clang/snpe-tensorflow-to-dlc", line 56, in main
    optimized_graph = optimizer.optimize(ir_graph)
  File "/home/snpe/snpe-1.52.0.2724/lib/python/qti/aisw/converters/common/converter_ir/op_graph_optimizations.py", line 196, in optimize
    remove_disconnected_nodes(graph)
  File "/home/snpe/snpe-1.52.0.2724/lib/python/qti/aisw/converters/common/converter_ir/op_graph_optimizations.py", line 413, in remove_disconnected_nodes
    raise ValueError("After pruning disconnected nodes, this model is empty.")
ValueError: After pruning disconnected nodes, this model is empty.
 

Is anyone can help me out ?

snpe version = 1.52

tensoeflow=1.15

  • Up0
  • Down0
Re: After pruning disconnected nodes, this model is empty
shanghui_eml
Join Date: 13 Oct 21
Posts: 6
Posted: Thu, 2021-10-14 23:33
Top

[Update]This error has benn solved. The name of input_node is  "Preprocessor/sub""

  • Up0
  • Down0
or Register

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.