aboutsummaryrefslogtreecommitdiff
path: root/src/core/CL/kernels/CLPoolingLayerKernel.cpp
diff options
context:
space:
mode:
authorGeorgios Pinitas <georgios.pinitas@arm.com>2017-10-19 18:35:59 +0100
committerAnthony Barbier <anthony.barbier@arm.com>2018-11-02 16:35:24 +0000
commit13fc22c3c3f609489e53ec706026a2a7991bf367 (patch)
tree871d9c949ce9d10f0d65ffa37365b9bd28779e3b /src/core/CL/kernels/CLPoolingLayerKernel.cpp
parent4398becc0ae11f346e1669a9b5210ef389bd8012 (diff)
downloadComputeLibrary-13fc22c3c3f609489e53ec706026a2a7991bf367.tar.gz
COMPMID-556: Fix CLPoolingLayer checks
Change-Id: Ib76554adf00fb3c1943da634dc948089843f0e78 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/92439 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'src/core/CL/kernels/CLPoolingLayerKernel.cpp')
-rw-r--r--src/core/CL/kernels/CLPoolingLayerKernel.cpp3
1 files changed, 1 insertions, 2 deletions
diff --git a/src/core/CL/kernels/CLPoolingLayerKernel.cpp b/src/core/CL/kernels/CLPoolingLayerKernel.cpp
index 497e87b2b5..542d5dcf9f 100644
--- a/src/core/CL/kernels/CLPoolingLayerKernel.cpp
+++ b/src/core/CL/kernels/CLPoolingLayerKernel.cpp
@@ -67,7 +67,6 @@ void CLPoolingLayerKernel::configure(const ICLTensor *input, ICLTensor *output,
ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(input, 1, DataType::QS8, DataType::QS16, DataType::F16, DataType::F32);
ARM_COMPUTE_ERROR_ON_NULLPTR(output);
ARM_COMPUTE_ERROR_ON(pool_pad_x >= pool_size || pool_pad_y >= pool_size);
- ARM_COMPUTE_ERROR_ON(pool_size > 7 && is_data_type_fixed_point(input->info()->data_type()));
// Check output dimensions
std::tie(pooled_w, pooled_h) = scaled_dimensions(input->info()->dimension(0),
@@ -118,7 +117,7 @@ void CLPoolingLayerKernel::configure(const ICLTensor *input, ICLTensor *output,
}
// Create kernel
- if(pool_size <= 7)
+ if((pool_size == 2) || (pool_size == 3) || (pool_size == 7))
{
// Check if we have pool3x3 with stride_x less equal than 3. In these cases, run an optimized OpenCL kernel where
// each thread computes 4 output elements