Forums - Couldn't initialize Htp Offline Prepare Backend

5 posts / 0 new

or Register

Last post

Couldn't initialize Htp Offline Prepare Backend

lijun16

Join Date: 20 Dec 20

Posts: 1

Posted: Sat, 2021-02-27 23:48

Top

Hello, I am trying to run

snpe-dlc-quantize --input_dlc inception_v3.dlc --input_list /home/snpe-1.45.3.2435/models/inception_v3/data/cropped/raw_list.txt --output_dlc inception_v3_quantized.dlc --enable_htp

Error report due to using --enable_htp

[INFO] Writing quantized model to: inception_v3_quantized.dlc
[ERROR] SnpeQnnController::Load Cannot load symbol QnnBackend_initialize : snpe-dlc-quantize: undefined symbol: QnnBackend_initialize
[ERROR] Unable to loadQnnFunction QnnBackend_initialize
[ERROR] SnpeQnnController::Load Cannot load symbol QnnBackend_terminate : snpe-dlc-quantize: undefined symbol: QnnBackend_terminate
[ERROR] Unable to loadQnnFunction QnnBackend_terminate

.....

Couldn't initialize Htp Offline Prepare Backend

I do not understand why this error is happening or how to fix it. Any help or insight would be greatly apprectiate

Forum vote up/down

Re: Couldn't initialize Htp Offline Prepare Backend #1

zhangyiyang049

Join Date: 4 Mar 21

Posts: 1

Posted: Thu, 2021-03-04 06:08

Top

got the save problem trying to quatify a dlc (transferred from onnx) with '--enable_htp'

snpe version==1.47.0.2501

it runs fine without '--enable_htp' but once added it crushed

then i tried '--enable_hta' and it crushed too, with outputs :

Quantization not specified in DLC

[INFO] Blob ID:2

[ERROR] Automatic partitioning failed. Error code: 8

[INFO] Writing quantized model to: ./int8_net_alt0.dlc

[INFO] Compiling HTA metadata into DLC.

[ERROR] Layer output_1 doesn't exist in the network.

[ERROR] Invalid output layers specified.

[ERROR] Initial setup failed.

[ERROR] Couldn't compile HTA metadata into DLC.

does any one get a solution? thanks very much !

Re: Couldn't initialize Htp Offline Prepare Backend #2

zhangshuai14

Join Date: 19 Aug 21

Posts: 1

Posted: Wed, 2021-10-13 23:58

Top

The same ERROR reported when using --enable_htp.

------

I checked the dependencies once again, and installed the libc++-9-dev using: sudo apt-get install libc++-9-dev=1:9-2~ubuntu18.04.2.

As a result, the error disappeared.

-----

I also installed the clang: sudo apt-get install clang

Re: Couldn't initialize Htp Offline Prepare Backend #3

andrii.tsarov

Join Date: 30 Jun 21

Posts: 4

Posted: Mon, 2022-04-11 19:04

Top

I faced the similar issue - carsh after enabling --enable-hta function. Turned out that snpe-dlc-quantize was trying to load symbol from library that is not in the LD_LIBRARY_PATH.

1) Search which library has the symbol and it's path

user@ubuntu:~/work/snpe-1.60.0.3313$ grep -r QnnInterface_getProviders *
Binary file bin/x86_64-linux-clang/snpe-dlc-quantize matches
Binary file lib/dsp/libsnpe_dsp_v68_domains_v3_skel.so matches
Binary file lib/x86_64-linux-clang/libHtpPrepare.so matches

2) Update LD_LIBRARY_PATH
user@ubuntu:$ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$SNPE_ROOT/lib/x86_64-linux-clang/

Re: Couldn't initialize Htp Offline Prepare Backend #4

bharat.mohan

Join Date: 23 Feb 22

Posts: 1

Posted: Fri, 2022-07-29 23:58

Top

I am facing the same issue. The path to HTP backends are set in LD_LIBRARY_PATH. I am using SNPE-1.54. Please see the logs below:

[INFO] Writing quantized model to:

***

[ERROR] SnpeQnnController::Load Cannot load symbol QnnBackend_initialize : snpe-dlc-quantize: undefined symbol: QnnBackend_initialize

[ERROR] Unable to loadQnnFunction QnnBackend_initialize

[ERROR] SnpeQnnController::Load Cannot load symbol QnnBackend_terminate : snpe-dlc-quantize: undefined symbol: QnnBackend_terminate

[ERROR] Unable to loadQnnFunction QnnBackend_terminate

[ERROR] SnpeQnnController::Load Cannot load symbol QnnBackend_registerOpPackage : snpe-dlc-quantize: undefined symbol: QnnBackend_registerOpPackage

[ERROR] Unable to loadQnnFunction QnnBackend_registerOpPackage

[ERROR] SnpeQnnController::Load Cannot load symbol QnnBackend_getPerfInfrastructure : snpe-dlc-quantize: undefined symbol: QnnBackend_getPerfInfrastructure

[ERROR] Unable to loadQnnFunction QnnBackend_getPerfInfrastructure

[ERROR] SnpeQnnController::Load Cannot load symbol QnnContext_create : snpe-dlc-quantize: undefined symbol: QnnContext_create

[ERROR] Unable to loadQnnFunction QnnContext_create

[ERROR] SnpeQnnController::Load Cannot load symbol QnnContext_free : snpe-dlc-quantize: undefined symbol: QnnContext_free

[ERROR] Unable to loadQnnFunction QnnContext_free

[ERROR] SnpeQnnController::Load Cannot load symbol QnnContext_getBinarySize : snpe-dlc-quantize: undefined symbol: QnnContext_getBinarySize

[ERROR] Unable to loadQnnFunction QnnContext_getBinarySize

[ERROR] SnpeQnnController::Load Cannot load symbol QnnContext_getBinary : snpe-dlc-quantize: undefined symbol: QnnContext_getBinary

[ERROR] Unable to loadQnnFunction QnnContext_getBinary

[ERROR] SnpeQnnController::Load Cannot load symbol QnnContext_createFromBinary : snpe-dlc-quantize: undefined symbol: QnnContext_createFromBinary

[ERROR] Unable to loadQnnFunction QnnContext_createFromBinary

[ERROR] SnpeQnnController::Load Cannot load symbol QnnContext_setConfig : snpe-dlc-quantize: undefined symbol: QnnContext_setConfig

[ERROR] Unable to loadQnnFunction QnnContext_setConfig

[ERROR] SnpeQnnController::Load Cannot load symbol QnnGraph_create : snpe-dlc-quantize: undefined symbol: QnnGraph_create

[ERROR] Unable to loadQnnFunction QnnGraph_create

[ERROR] SnpeQnnController::Load Cannot load symbol QnnGraph_addNode : snpe-dlc-quantize: undefined symbol: QnnGraph_addNode

[ERROR] Unable to loadQnnFunction QnnGraph_addNode

[ERROR] SnpeQnnController::Load Cannot load symbol QnnGraph_finalize : snpe-dlc-quantize: undefined symbol: QnnGraph_finalize

[ERROR] Unable to loadQnnFunction QnnGraph_finalize

[ERROR] SnpeQnnController::Load Cannot load symbol QnnGraph_execute : snpe-dlc-quantize: undefined symbol: QnnGraph_execute

[ERROR] Unable to loadQnnFunction QnnGraph_execute

[ERROR] SnpeQnnController::Load Cannot load symbol QnnGraph_retrieve : snpe-dlc-quantize: undefined symbol: QnnGraph_retrieve

[ERROR] Unable to loadQnnFunction QnnGraph_retrieve

[ERROR] SnpeQnnController::Load Cannot load symbol QnnProfile_create : snpe-dlc-quantize: undefined symbol: QnnProfile_create

[ERROR] Unable to loadQnnFunction QnnProfile_create

[ERROR] SnpeQnnController::Load Cannot load symbol QnnProfile_getEvents : snpe-dlc-quantize: undefined symbol: QnnProfile_getEvents

[ERROR] Unable to loadQnnFunction QnnProfile_getEvents

[ERROR] SnpeQnnController::Load Cannot load symbol QnnProfile_getSubEvents : snpe-dlc-quantize: undefined symbol: QnnProfile_getSubEvents

[ERROR] Unable to loadQnnFunction QnnProfile_getSubEvents

[ERROR] SnpeQnnController::Load Cannot load symbol QnnProfile_getEventData : snpe-dlc-quantize: undefined symbol: QnnProfile_getEventData

[ERROR] Unable to loadQnnFunction QnnProfile_getEventData

[ERROR] SnpeQnnController::Load Cannot load symbol QnnTensor_createContextTensor : snpe-dlc-quantize: undefined symbol: QnnTensor_createContextTensor

[ERROR] Unable to loadQnnFunction QnnTensor_createContextTensor

[ERROR] SnpeQnnController::Load Cannot load symbol QnnTensor_createGraphTensor : snpe-dlc-quantize: undefined symbol: QnnTensor_createGraphTensor

[ERROR] Unable to loadQnnFunction QnnTensor_createGraphTensor

[ERROR] Couldn't initialize Htp Offline Prepare Backend.

[INFO] DebugLog shutting down.

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.

Sort By

Filter Results