COMPMID-3100 Fuse bias addition with fully connected layer NEON
NEGEMM and NEGEMMLowpMatrixMultiplyCore are already fuse with bias
addition. Expose them to NEFullyConnectedLayer.
Change-Id: I42a909565bf49de1a019a07dc4dca11ae0981ada
Signed-off-by: SiCongLi <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2769
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
diff --git a/examples/graph_deepspeech_v0_4_1.cpp b/examples/graph_deepspeech_v0_4_1.cpp
index d2a4832..ed44ffb 100644
--- a/examples/graph_deepspeech_v0_4_1.cpp
+++ b/examples/graph_deepspeech_v0_4_1.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2019 ARM Limited.
+ * Copyright (c) 2019-2020 ARM Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -57,9 +57,6 @@
return false;
}
- // Checks
- ARM_COMPUTE_EXIT_ON_MSG(arm_compute::is_data_type_quantized_asymmetric(common_params.data_type), "QASYMM8 not supported for this graph");
-
// Print parameter values
std::cout << common_params << std::endl;