Bureaucrats, dave_user, Administrators
4,650
edits
Changes
→Coarse grained profiling using DNNDK low level API
</pre>
Within the scope of this TN, the most relevant time is ''DPU tot time'', which indicates the time spent to execute the inference (~3.7ms). This leads to a throughput of about 271 fps.
====Fine grained profiling using DNNDK low level API====
