Support dynamic weights for Fully Connected layers on GPU
The fully connected function and operator running on GPU have been adapted to support dynamic weights.
Dynamic weights require the reshape and data layout conversion of weight tensors at runtime in the prepare stage of the operator. The implementation for GPU is identical to the CPU implementation.
This patch also deprecates the `are_weights_reshaped` option in Fully Connected.
Resolves: COMPMID-5870
Change-Id: I28f967695879d82cc91a928d95308a4e0e52a597
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9403
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/core/Types.h b/arm_compute/core/Types.h
index 8434611..fd45bba 100644
--- a/arm_compute/core/Types.h
+++ b/arm_compute/core/Types.h
@@ -1833,7 +1833,7 @@
/* Information about weights */
DataLayout weights_trained_layout{ DataLayout::NCHW }; /**< Layout that the weights have been trained with. */
bool transpose_weights{ true }; /**< Transpose weights if true. */
- bool are_weights_reshaped{ false }; /**< Reshape the weights tensor if false. */
+ bool are_weights_reshaped{ false }; /**< @deprecated Reshape the weights tensor if false. */
bool retain_internal_weights{ false }; /**< Retain internal reshaped weights. */
bool enable_fast_math{ false }; /**< Enable fast math computation. */
/* Other parameters */