microsoft / microsoft/onnxruntime-inference-examples
Facing Errors while running example through dsp
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 1.7k
- Forks
- 414
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 14
Description
@HectorSVC I have gone through the steps at https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_cxx/Snpe_EP, but I am facing following errors in running the snpe_ep_sample --dsp chairs.raw command.
Error:-
linker : normalize_path - invalid input: "'/data/local/TMP/snpeexample'", the input path should be absolute
snpe_ep_example: vendor/qcom/proprietary/adsprpc/src/log_config.c:268:Error 0x200: fopen failed for /vendor/lib/rfsa/adsp/snpe_ep_sample.farf. (No such file or directory)
snpe_ep_example: vendor/qcom/proprietary/adsprpc/src/log_config.c:268:Error 0x200: fopen failed for /vendor/dsp/cdsp/snpe_ep_sample.farf. (No such file or directory)
snpe_ep_example: vendor/qcom/proprietary/adsprpc/src/log_config.c:268:Error 0x200: fopen failed for /vendor/dsp/snpe_ep_sample.farf. (No such file or directory)
I have tried it on Samsung galaxy S22 ultra device and with following versions:-
NDK version 25.1.8937393
SNPE 1.66.0.3729
Please let me know if I should change anything or if there are any other pre-requisite for successfully running the example.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the c_cxx/Snpe_EP example instructions and the snpe_ep_sample --dsp chairs.raw command, then compare the reported path and missing .farf errors with the stated NDK 25.1.8937393 and SNPE 1.66.0.3729 versions. Done means identifying the missing prerequisite or configuration and running the example successfully on the target device.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- android, cpp
- Domain
- machine-learning, mobile-dev
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100