COMPMID-1257: Allow retaining weights in CLDeconvolutionLayer
Change-Id: I8c430f2efafa0f47e2b12e388713ba693a6df8ee
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/134467
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
index 97998b5..82bb71c 100644
--- a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
@@ -74,7 +74,7 @@
* @param[in] output Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
* Data types supported: Same as @p input.
* @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo.
- * @param[in] weights_info Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel. Data type supported: Same as @p input.
+ * @param[in] weights_info Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel.
* @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
* @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
@@ -93,7 +93,7 @@
* @param[in] output Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
* Data types supported: Same as @p input.
* @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo.
- * @param[in] weights_info Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel. Data type supported: Same as @p input.
+ * @param[in] weights_info Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
* @param[in] gpu_target Specifies the @p GPUTarget.
* @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
diff --git a/arm_compute/runtime/CL/functions/CLDeconvolutionLayer.h b/arm_compute/runtime/CL/functions/CLDeconvolutionLayer.h
index f29039a..8296930 100644
--- a/arm_compute/runtime/CL/functions/CLDeconvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLDeconvolutionLayer.h
@@ -71,10 +71,11 @@
* @param[in] info Contains padding and policies to be used in the deconvolution, this is decribed in @ref PadStrideInfo.
* @param[in] inner_border_right The number of zeros added to right edge of the input.
* @param[in] inner_border_top The number of zeros added to top edge of the input.
+ * @param[in] weights_info (Optional) Weights information needed for @ref CLConvolutionLayer, specifies if the weights tensor has been reshaped with @ref CLWeightsReshapeKernel.
*
*/
void configure(ICLTensor *input, const ICLTensor *weights, const ICLTensor *bias, ICLTensor *output, const PadStrideInfo &info,
- unsigned int inner_border_right, unsigned int inner_border_top);
+ unsigned int inner_border_right, unsigned int inner_border_top, const WeightsInfo &weights_info = WeightsInfo());
/** Static function to check if given info will lead to a valid configuration of @ref CLDeconvolutionLayer
*
* @param[in] input Input tensor info. 3 lower dimensions represent a single input, and an optional 4th dimension for batch of inputs. Data types supported: F16/F32.
@@ -84,11 +85,12 @@
* @param[in] info Contains padding and policies to be used in the deconvolution, this is decribed in @ref PadStrideInfo.
* @param[in] inner_border_right The number of zeros added to right edge of the input.
* @param[in] inner_border_top The number of zeros added to top edge of the input.
+ * @param[in] weights_info (Optional) Weights information needed for @ref CLConvolutionLayer, specifies if the weights tensor has been reshaped with @ref CLWeightsReshapeKernel.
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *bias, ITensorInfo *output, const PadStrideInfo &info,
- unsigned int inner_border_right, unsigned int inner_border_top);
+ unsigned int inner_border_right, unsigned int inner_border_top, const WeightsInfo &weights_info = WeightsInfo());
// Inherited methods overridden:
void run() override;
@@ -100,4 +102,4 @@
CLTensor _scaled_output;
};
}
-#endif /* __ARM_COMPUTE_CLDECONVOLUTIONLAYER_H__ */
\ No newline at end of file
+#endif /* __ARM_COMPUTE_CLDECONVOLUTIONLAYER_H__ */
diff --git a/src/runtime/CL/functions/CLDeconvolutionLayer.cpp b/src/runtime/CL/functions/CLDeconvolutionLayer.cpp
index 4d971f3..6c54b18 100644
--- a/src/runtime/CL/functions/CLDeconvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLDeconvolutionLayer.cpp
@@ -43,7 +43,7 @@
}
Status CLDeconvolutionLayer::validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *bias, ITensorInfo *output, const PadStrideInfo &info,
- unsigned int inner_border_right, unsigned int inner_border_top)
+ unsigned int inner_border_right, unsigned int inner_border_top, const WeightsInfo &weights_info)
{
ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(input, weights, output);
ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(input, 1, DataType::F16, DataType::F32);
@@ -80,13 +80,13 @@
const PadStrideInfo conv_info(1, 1, 0, 0, 0, 0, DimensionRoundingType::CEIL);
ARM_COMPUTE_RETURN_ON_ERROR(CLDeconvolutionLayerUpsample::validate(input, &scale_out_info, BorderSize(inner_border_right, inner_border_top), info));
- ARM_COMPUTE_RETURN_ON_ERROR(CLConvolutionLayer::validate(&scale_out_info, weights, bias, output, conv_info, WeightsInfo()));
+ ARM_COMPUTE_RETURN_ON_ERROR(CLConvolutionLayer::validate(&scale_out_info, weights, bias, output, conv_info, weights_info));
return Status{};
}
void CLDeconvolutionLayer::configure(ICLTensor *input, const ICLTensor *weights, const ICLTensor *bias, ICLTensor *output, const PadStrideInfo &info,
- unsigned int inner_border_right, unsigned int inner_border_top)
+ unsigned int inner_border_right, unsigned int inner_border_top, const WeightsInfo &weights_info)
{
ARM_COMPUTE_ERROR_ON_NULLPTR(input, weights, output);
@@ -120,7 +120,7 @@
// setup the function to convolve the upscaled output
const PadStrideInfo conv_info(1, 1, 0, 0, 0, 0, DimensionRoundingType::CEIL);
- _conv_f.configure(&_scaled_output, weights, bias, output, conv_info);
+ _conv_f.configure(&_scaled_output, weights, bias, output, conv_info, weights_info);
_scaled_output.allocator()->allocate();
}