Other Parts Discussed in Thread: AM69A
Hi, friends.
In SDK0804, Number of batches to be processed together by setting numBatches option.
So,how to configure this option in edgeai-tidl-tools?
Best Regards
Henry
This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
Hi,
Please refer the edgeai tidl tools documents :
To enable parallel batch processing, set the options as follows: advanced_options:inference_mode = 1 advanced_options:num_cores = Number of batches in the model
Hi,Pratik
Thank you for the reply.
I want to use this feature on SDK 08_06_00_12 TDA4VM.So I used edgeai-tidl-tools tag 08_06_00_03 according to https://github.com/TexasInstruments/docs/version_compatibility_table.md.
We do not see the options[inference_mode/num_cores ] in this version of common_utils.py.
And i notice the options are applicable only for "AM69A"
Can you tell me how to deploy this feature on SDK 08_06_00_12 TDA4VM.
Best Regards
Henry
Hi,
Parallel Batch Processing is only supported for multi core devices like AM69A only.
Secondly this support is only available post 9.0 SDK release.
We recommend to use appropriate SDK and Target SoC as mentioned above to enable this feature.
Hi,Pratik
If i want to develop in SDK9.0, which tag of edgeai-tidl-tools should i use?
https://github.com/TexasInstruments/docs/version_compatibility_table.md this page is not found now.
Best Regards
Henry
Click on the tag section of the repo there you will find all the tags.
09_00_00_06