dave_user
207
edits
Changes
no edit summary
==Comparison==
[[File:Pre and post quantization accuracy.png|center|thumb|500x500px|Models pre and post quantization accuracy with vai_q_tensorflow tool]]
<!--Start of table definition-->
|-align="center"
|
|[[File:Inception resnet v2 cores utilizationDPU Kernel parameters size.png|thumb|250x250px500x500px|Utilization of CPU and Deployed models DPU cores of Inception ResNet V2 model for 1, 2, and 4 threadsKernel parameters size]]
|
|[[File:Inception resnet v2 DPU Kernel total tensor count.png|thumb|500x500px|Deployed models DPU Kernel total tensor count]]||} [[File:DPU throughput for 1-2-4 threads.png|center|thumb|500x500px|Deployed models DPU throughput for 1, 2, and 4 threads]] <!--Start of table definition-->{|style="background:transparent; color:black" border="0" height="550" align="center" valign="bottom" cellpadding=10px cellspacing=0px|-align="center"||[[File:DPU-00 core latencyfor 1-2-4 threads.png|thumb|250x250px500x500px|Deployed models DPU -00 core latency for [1,2,4] threads]]||[[File:DPU-01 core latency for 1-2-4 threads.png|thumb|500x500px|Deployed models DPU-01 core latency of Inception ResNet V2 model for [1, 2, and 4 ] threads]]
|
|}
