Chen Feiyue 61ea0091ca Fixed unsupported float16 bias in fc (#646) ... Resolve the issue of underlying hardware not supporting float16 bias in fc by converting bias type to float32 Type: Code Improvement Signed-off-by: Feiyue Chen <Feiyue.Chen@verisilicon.com>		2023-09-13 09:44:21 +08:00
..
ops	Fixed unsupported float16 bias in fc (#646)	2023-09-13 09:44:21 +08:00
platform	Fixed IExecutable object not bind with DeviceID (#624)	2023-07-24 22:45:54 +08:00
builtin_op.h	update copyright information	2023-01-20 12:49:48 +08:00
compile_option.h	Fixed IExecutable object not bind with DeviceID (#624)	2023-07-24 22:45:54 +08:00
context.h	update copyright information	2023-01-20 12:49:48 +08:00
graph.h	Added op fusion for mean_stddev_normalization (#629)	2023-08-09 22:10:45 +08:00
operation.h	Enable float16 bias convolution model runs on NN (#612)	2023-06-30 09:41:28 +08:00
ops.h	optimization for tiny_yolov4 (#591)	2023-05-23 14:28:47 +08:00
tensor.h	build fix for export Swap Handle API (#643)	2023-08-30 14:25:45 +08:00
types.h	Refine Tensor::SetShape api to avoid compile warning using const ref (#640)	2023-08-25 00:47:24 +08:00