Part Number: TDA3MA
Softmax layer contains floating point calculation, which cannot be executed on vcop, but it will be very slow on arp32. How to solve this problem?
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.
Part Number: TDA3MA
Softmax layer contains floating point calculation, which cannot be executed on vcop, but it will be very slow on arp32. How to solve this problem?
Hi,
Yes, softmax layer contains floating point calculation so it is not recommended to run this layer on EVE core. We would suggest to run this layer on DSP core.
Thanks,
Praveen