COMPMID-1586: Add support for NHWC CLDeconvolutionLayer

COMPMID-1651: Fix QASYMM8 CLDeconvolutionLayer

This patch also extends the range of values used for testing Convolution and
Deconvolution to cover quantized [-1.0f, 1.0f].

Change-Id: I8b280669db67bb3ec25bf5d411c8f5954f5b0dab
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149869
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>

1 files changed, 34 insertions, 26 deletions

diff --git a/src/runtime/CL/functions/CLDeconvolutionLayer.cpp b/src/runtime/CL/functions/CLDeconvolutionLayer.cpp
index 26d44e9c96..951d1ec4f0 100644
--- a/src/runtime/CL/functions/CLDeconvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLDeconvolutionLayer.cpp
@@ -53,8 +53,16 @@ Status CLDeconvolutionLayer::validate(const ITensorInfo *input, const ITensorInf
 {
     ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(input, weights, output);
     ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(input, 1, DataType::QASYMM8, DataType::F16, DataType::F32);
-    ARM_COMPUTE_RETURN_ERROR_ON(weights->dimension(0) != weights->dimension(1));
-    ARM_COMPUTE_RETURN_ERROR_ON(weights->dimension(0) < 1);
+    ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_LAYOUT(input, weights);
+
+    const DataLayout data_layout = input->data_layout();
+
+    const size_t idx_w = get_data_layout_dimension_index(data_layout, DataLayoutDimension::WIDTH);
+    const size_t idx_h = get_data_layout_dimension_index(data_layout, DataLayoutDimension::HEIGHT);
+    const size_t idx_c = get_data_layout_dimension_index(data_layout, DataLayoutDimension::CHANNEL);
+
+    ARM_COMPUTE_RETURN_ERROR_ON(weights->dimension(idx_w) != weights->dimension(idx_h));
+    ARM_COMPUTE_RETURN_ERROR_ON(weights->dimension(idx_w) < 1);
     ARM_COMPUTE_RETURN_ERROR_ON(!info.padding_is_symmetric());
 
     const unsigned int stride_x = info.stride().first;
@@ -63,10 +71,10 @@ Status CLDeconvolutionLayer::validate(const ITensorInfo *input, const ITensorInf
     ARM_COMPUTE_RETURN_ERROR_ON_MSG(inner_border_right > stride_x - 1, "inner_border_right must be smaller than stride_x");
     ARM_COMPUTE_RETURN_ERROR_ON_MSG(inner_border_top > stride_y - 1, "inner_border_top must be smaller than stride_y");
 
-    auto out_dims = deconvolution_output_dimensions(input->dimension(0), input->dimension(1), weights->dimension(0), weights->dimension(1),
+    auto out_dims = deconvolution_output_dimensions(input->dimension(idx_w), input->dimension(idx_h), weights->dimension(idx_w), weights->dimension(idx_h),
                                                     info.pad().first, info.pad().second, stride_x, stride_y);
 
-    const TensorShape output_shape = deconvolution_output_shape(out_dims, input->tensor_shape(), weights->tensor_shape());
+    const TensorShape output_shape = compute_deconvolution_output_shape(out_dims, *input, *weights);
 
     ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(input, output, weights);
 
@@ -80,15 +88,17 @@ Status CLDeconvolutionLayer::validate(const ITensorInfo *input, const ITensorInf
         {
             ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(input, bias);
         }
+        ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_LAYOUT(input, bias);
     }
 
-    ARM_COMPUTE_RETURN_ERROR_ON_MSG(output->dimension(Window::DimX) != output_shape.x(), "Output's width is invalid.");
-    ARM_COMPUTE_RETURN_ERROR_ON_MSG(output->dimension(Window::DimY) != output_shape.y(), "Output's height is invalid.");
-    ARM_COMPUTE_RETURN_ERROR_ON_MSG(output->dimension(Window::DimZ) != output_shape.z(), "Output's depth is invalid.");
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(output->dimension(idx_w) != output_shape[idx_w], "Output's width is invalid.");
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(output->dimension(idx_h) != output_shape[idx_h], "Output's height is invalid.");
+    ARM_COMPUTE_RETURN_ERROR_ON_MSG(output->dimension(idx_c) != output_shape[idx_c], "Output's depth is invalid.");
 
-    TensorInfo scale_out_info(input->clone()->set_is_resizable(true).reset_padding().set_tensor_shape(compute_deconvolution_shape(*input, *weights, stride_x, stride_y, inner_border_right,
-                                                                                                      inner_border_top,
-                                                                                                      out_dims)));
+    unsigned int        padx            = 0;
+    unsigned int        pady            = 0;
+    const TensorShape   scale_out_shape = compute_deconvolution_upsampled_shape(*input, *weights, stride_x, stride_y, inner_border_right, inner_border_top, out_dims, padx, pady);
+    TensorInfo          scale_out_info(input->clone()->set_is_resizable(true).reset_padding().set_tensor_shape(scale_out_shape).set_data_layout(data_layout));
     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));
@@ -105,17 +115,22 @@ void CLDeconvolutionLayer::configure(ICLTensor *input, ICLTensor *weights, const
     const unsigned int stride_x = info.stride().first;
     const unsigned int stride_y = info.stride().second;
 
+    const DataLayout data_layout = input->info()->data_layout();
+
+    const size_t idx_w = get_data_layout_dimension_index(data_layout, DataLayoutDimension::WIDTH);
+    const size_t idx_h = get_data_layout_dimension_index(data_layout, DataLayoutDimension::HEIGHT);
+
     _weights = weights;
-    _weights_flipped.allocator()->init(TensorInfo(weights->info()->tensor_shape(), 1, weights->info()->data_type()));
+    _weights_flipped.allocator()->init(weights->info()->clone()->set_data_layout(data_layout));
     _flip_weights.configure(weights, &_weights_flipped);
 
-    auto out_dims = deconvolution_output_dimensions(input->info()->dimension(0), input->info()->dimension(1), weights->info()->dimension(0), weights->info()->dimension(1),
+    auto out_dims = deconvolution_output_dimensions(input->info()->dimension(idx_w), input->info()->dimension(idx_h), weights->info()->dimension(idx_w), weights->info()->dimension(idx_h),
                                                     info.pad().first, info.pad().second, stride_x, stride_y);
 
-    const TensorShape output_shape = deconvolution_output_shape(out_dims, input->info()->tensor_shape(), weights->info()->tensor_shape());
+    const TensorShape output_shape = compute_deconvolution_output_shape(out_dims, *input->info(), *weights->info());
 
     // Output auto initialization if not yet initialized
-    auto_init_if_empty(*output->info(), output_shape, 1, input->info()->data_type(), input->info()->quantization_info());
+    auto_init_if_empty(*output->info(), input->info()->clone()->set_tensor_shape(output_shape).set_data_layout(data_layout));
 
     // Perform validation step
     ARM_COMPUTE_ERROR_THROW_ON(CLDeconvolutionLayer::validate(input->info(), weights->info(), bias == nullptr ? nullptr : bias->info(), output->info(), info, inner_border_right, inner_border_top));
@@ -125,20 +140,13 @@ void CLDeconvolutionLayer::configure(ICLTensor *input, ICLTensor *weights, const
     _memory_group.manage(&_scaled_output);
     _memory_group.manage(&_weights_flipped);
 
-    // Find the upsampled dimensions
-    unsigned int out_x = (input->info()->dimension(0) - 1) * stride_x + inner_border_right + 1;
-    unsigned int out_y = (input->info()->dimension(1) - 1) * stride_y + inner_border_top + 1;
-
-    // Find the padding needed for the convolution with stride 1 in order to match output shape
-    unsigned int padx = out_dims.first - (out_x - weights->info()->dimension(0) + 1);
-    unsigned int pady = out_dims.second - (out_y - weights->info()->dimension(1) + 1);
-    out_x += padx;
-    out_y += pady;
+    // Find the upsampled dimensions and the padding needed for the convolution with stride 1 in order to match output shape
+    unsigned int      padx            = 0;
+    unsigned int      pady            = 0;
+    const TensorShape scale_out_shape = compute_deconvolution_upsampled_shape(*input->info(), *weights->info(), stride_x, stride_y, inner_border_right, inner_border_top, out_dims, padx, pady);
 
-    TensorShape scale_out_shape(input->info()->tensor_shape());
-    scale_out_shape.set(0, out_x);
-    scale_out_shape.set(1, out_y);
     TensorInfo scale_out_info(scale_out_shape, 1, input->info()->data_type(), input->info()->quantization_info());
+    scale_out_info.set_data_layout(data_layout);
     _scaled_output.allocator()->init(scale_out_info);
 
     // configure scale function