• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 102 subscribers
  • Views 84 views
  • Users 0 members are here
Support feedback
Options
Options
Similar topics

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.

TDA4VM: Configure batch processing using edgeai-tidl-tools

Aleksandar Vujinovic
Prodigy 30 points
Part Number: TDA4VM

Tool/software:

Hi TI Team,

Is it possible to enable batch processing on single-core architectures using edgeai-tidl-tools ? It seems that only parallel batch processing is enabled by configuring advanced_options:inference_mode and advanced_options:num_cores.

NOTE:

I've tried using import tools (psdk versions: 09.01.00.06 and  10.00.00.05)  and setting the numBatches parameter to the desired batch size. With that, I compiled and executed the model on the target, but the correct results were present only for the first batch.