tree 78e8a9abfefc6db67f9a71f6c1fddb0444daac5f
parent 5716de25c6981d004e32b81dc65b4869eda25f7c
author Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> 1573658188 +0000
committer Áron Virginás-Tar <aron.virginas-tar@arm.com> 1573836887 +0000

IVGCVSW-4119 Fix FP16 to FP32 fallback mechanism in optimizer to work with Dequantize

* Check for output data type as well as input data type when determining
  whether we should attempt to fall back to FP32 if FP16 is not supported
* Override output type for Dequantize in IsLayerSupported() instead of
  input type
* Updated original input type from FP16 to FP32 in InsertConvertFp32ToFp16LayersAfter()

Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Ic6477fd17cea5a91bd8bf9ae0cf836520897d5b7