commit 6e10aa395e81b83edb3437191acd7abe1639c7dc
author Manuel Bottini <manuel.bottini@arm.com> Thu Apr 30 13:28:23 2020 +0100
committer Manuel Bottini <manuel.bottini@arm.com> Tue May 12 09:34:17 2020 +0000
tree fce78e75102402df6dbbd37e715f9ef855846008
parent 0e240151637641e9e0c425d52dd75b7bd11d1159

COMPMID-3316: NEDeconvolutionLayer failing for a big input

- Using NEDirectConvolution for big shapes since the memory
  required explodes for 9x9 kernel
- Adding test cases
- Fix enables only the NEON Deconvolution for NHWC

Change-Id: I8a541346428e5686818f8ecb7f69e2a9106cbceb
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3135
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>

src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp

diff --git a/src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp b/src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp
index 6553884..751a3fa 100644
--- a/src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp
+++ b/src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2019 ARM Limited.
+ * Copyright (c) 2017-2020 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -76,7 +76,8 @@
 {
     ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(input, weights, output);
 
-    DataType   data_type = output->data_type();
+    // output might not be initialized since it can be an intermediate tensor of another layer
+    DataType   data_type = input->data_type();
     TensorInfo accumulator(output->clone()->set_is_resizable(true).reset_padding().set_data_type(data_type));
 
     // Validate Convolution kernel