COMPMID-3098 Fuse Relu and Bounded Relu with FullyConnected NEON
Change-Id: Id28062445590d6c06b35f7d7434eb38393ae94a7
Signed-off-by: SiCongLi <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2875
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/runtime/NEON/functions/NEFullyConnectedLayer.h b/arm_compute/runtime/NEON/functions/NEFullyConnectedLayer.h
index db09da4..b14650c 100644
--- a/arm_compute/runtime/NEON/functions/NEFullyConnectedLayer.h
+++ b/arm_compute/runtime/NEON/functions/NEFullyConnectedLayer.h
@@ -162,9 +162,9 @@
void prepare() override;
private:
- void configure_fc_fc(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output);
- void configure_conv_fc(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output);
- void configure_mm(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output);
+ void configure_fc_fc(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output, const ActivationLayerInfo &act);
+ void configure_conv_fc(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output, const ActivationLayerInfo &act);
+ void configure_mm(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output, const ActivationLayerInfo &act);
MemoryGroup _memory_group;
IWeightsManager *_weights_manager;
@@ -182,7 +182,7 @@
bool _are_weights_converted;
bool _are_weights_reshaped;
bool _is_fc_after_conv;
- bool _is_quantized;
+ bool _is_quantized_asymmetric;
bool _is_prepared;
};
} // namespace arm_compute