MLBEDSW-10181: Infer OFM shape if it's missing
There are cases where, for example, a QUANTIZE op has a constant
tensor input, but shapless output. With this patch, OFM will
inherit IFM's shape for certain ops.
Signed-off-by:
Johan Gunnarsson <johan.gunnarsson@arm.com>
Change-Id: Ibcdc503ed56cbe0822e3d5d33dfde76f5620cd07
parent
c9ed0bee
Loading
Loading
Pipeline
#21668
passed
with stages
in
3 minutes and 40 seconds
Loading
Please register or sign in to comment