diff options
author | Manuel Bottini <manuel.bottini@arm.com> | 2020-04-30 13:28:23 +0100 |
---|---|---|
committer | Manuel Bottini <manuel.bottini@arm.com> | 2020-05-12 09:34:17 +0000 |
commit | 6e10aa395e81b83edb3437191acd7abe1639c7dc (patch) | |
tree | fce78e75102402df6dbbd37e715f9ef855846008 /src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp | |
parent | 0e240151637641e9e0c425d52dd75b7bd11d1159 (diff) | |
download | ComputeLibrary-6e10aa395e81b83edb3437191acd7abe1639c7dc.tar.gz |
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>
Diffstat (limited to 'src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp')
-rw-r--r-- | src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp b/src/runtime/NEON/functions/NEDirectConvolutionLayer.cpp index 65538848df..751a3fa1fb 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 @@ Status NEDirectConvolutionLayer::validate(const ITensorInfo *input, const ITenso { 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 |