Forums - false execute

2 posts / 0 new
Last post
false execute
Join Date: 17 Jun 22
Posts: 1
Posted: Fri, 2022-06-17 04:11

I executed my ai model through the C++ apis. I've tested all runtimes, CPU,GPU,DSP,AIP.  CPU,GPU&DSP just worked fine.

When I execute the quantized model with --enable_hta in AIP runtim, snpe->execute(inputtensor.get(), outputTensorMap) returned false.

I didn't find any error through the logcat console:

E/npu_user_driver: NPU_Stats: npu_load_network(): 95.17 ms

E/npu_user_driver: NPU_Stats: npu_alloc_buffer_v2(): 0.08 ms sts=0


E/npu_user_driver: npu_set_property status: 0

Net Execute Failed   //this is a custom print code when snpe->execute returns false


E/npu_user_driver: * NPU_Stats: npu_free_buffer_v2(): 0.01 ms

E/npu_user_driver: * NPU_Stats: npu_unload_network(): 1607.50 ms

E/npu_user_driver: npu_set_property status: 0


Please help me debug this issue.

  • Up0
  • Down0
Join Date: 12 Apr 20
Posts: 103
Posted: Sat, 2022-06-18 18:38

Dear customer,

Could you please help to reply below confusion to us?

1 Which platform you used?

2 What's SNPE version you tested?

3 What's SNPE conversion and quantization commands you executed?



  • 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.