How can i run argmax on dla?

Hi, i am transferring a segmentation model from gpu to dla. But i find that the argmax layer is not supported. Is there any suggestion? Will you support it in the future? Thanks!


For non-supported layer, you can fallback it to GPU by enable the --allowGPUFallback.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.