MLBEDSW-5315 MLCE: Vela to handle skip Tensor
Removed graph optimizations no longer needed that caused problems
with FullyConnected operators running on CPU being consumed by
elementwise operators in Vela.
Signed-off-by:
Fredrik Svedberg <fredrik.svedberg@arm.com>
Change-Id: Ic7e66141ccd5e9aa8f0022c5ab9e7fd1ba3f6786
Loading
Please register or sign in to comment