Skip to content
Commit 1e22d965 authored by Sadik Armagan's avatar Sadik Armagan Committed by Cathal Corbett
Browse files

IVGCVSW-6954 'Arm NN SL Improvements' 



* Move the Conv2D and DepthwiseConv2D validation to Optimization level
  when the weights and tensors are as constant inputs
* Take into account offset and scales values when doing INT8 to FP32 dequantization

Signed-off-by: default avatarSadik Armagan <sadik.armagan@arm.com>
Change-Id: I1f81f15640395ac041923b10dbe9151159715117
parent 560c3938
Hide whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment