DownMix Node and to_decibels augmentations

CHANGELOG.md

@@ -12,6 +12,7 @@ Documentation for MIVisionX is available at
 * Support for advanced GPUs
 * Support for PreEmphasis Filter augmentation in openVX extensions
 * Support for Spectrogram augmentation in openVX extensions
+* Support for Downmix and ToDecibels augmentations in openVX extensions
 
 ### Optimizations
 

amd_openvx_extensions/amd_rpp/CMakeLists.txt

@@ -135,6 +135,7 @@ list(APPEND SOURCES
         source/tensor/Copy.cpp
         source/tensor/Crop.cpp
         source/tensor/CropMirrorNormalize.cpp
+        source/tensor/Downmix.cpp
         source/tensor/Exposure.cpp
         source/tensor/FishEye.cpp
         source/tensor/Flip.cpp
@@ -158,6 +159,7 @@ list(APPEND SOURCES
         source/tensor/SequenceRearrange.cpp
         source/tensor/Snow.cpp
         source/tensor/Spectrogram.cpp
+        source/tensor/ToDecibels.cpp
         source/tensor/Vignette.cpp
         source/tensor/WarpAffine.cpp
         source/tensor/SequenceRearrange.cpp

amd_openvx_extensions/amd_rpp/include/internal_publishKernels.h

@@ -157,6 +157,8 @@ vx_status Vignette_Register(vx_context);
 vx_status WarpAffine_Register(vx_context);
 vx_status SequenceRearrange_Register(vx_context);
 vx_status Spectrogram_Register(vx_context);
+vx_status Downmix_Register(vx_context);
+vx_status ToDecibels_Register(vx_context);
 
 // kernel names
 #define VX_KERNEL_RPP_NOPBATCHPD_NAME                           "org.rpp.NopbatchPD"
@@ -283,5 +285,7 @@ vx_status Spectrogram_Register(vx_context);
 #define VX_KERNEL_RPP_SEQUENCEREARRANGE_NAME                    "org.rpp.SequenceRearrange"
 #define VX_KERNEL_RPP_PREEMPHASISFILTER_NAME                    "org.rpp.PreemphasisFilter"
 #define VX_KERNEL_RPP_SPECTROGRAM_NAME                          "org.rpp.Spectrogram"
+#define VX_KERNEL_RPP_DOWNMIX_NAME                              "org.rpp.Downmix"
+#define VX_KERNEL_RPP_TODECIBELS_NAME                           "org.rpp.ToDecibels"
 
 #endif //_AMDVX_EXT__PUBLISH_KERNELS_H_

amd_openvx_extensions/amd_rpp/include/internal_rpp.h

@@ -43,6 +43,7 @@ THE SOFTWARE.
 #include<iostream>
 #include<algorithm>
 #include<functional>
+#include<map>
 
 using namespace std;
 
@@ -74,14 +75,25 @@ enum vxTensorLayout {
     VX_NTF = 6      // Time major, Used for Spectrogram/MelFilterBank
 };
 
+const std::map<vxTensorLayout, RpptLayout> tensorLayoutMapping = {
+    {vxTensorLayout::VX_NHWC, RpptLayout::NHWC},
+    {vxTensorLayout::VX_NCHW, RpptLayout::NCHW},
+    {vxTensorLayout::VX_NFHWC, RpptLayout::NHWC},
+    {vxTensorLayout::VX_NFCHW, RpptLayout::NCHW},
+#if RPP_AUDIO
+    {vxTensorLayout::VX_NHW, RpptLayout::NHW},
+    {vxTensorLayout::VX_NFT, RpptLayout::NFT},
+    {vxTensorLayout::VX_NTF, RpptLayout::NTF}
+#endif
+};
+
 //! Brief The utility functions
 vx_node createNode(vx_graph graph, vx_enum kernelEnum, vx_reference params[], vx_uint32 num);
 vx_status createRPPHandle(vx_node node, vxRppHandle ** pHandle, Rpp32u batchSize, Rpp32u deviceType);
 vx_status releaseRPPHandle(vx_node node, vxRppHandle * handle, Rpp32u deviceType);
 void fillDescriptionPtrfromDims(RpptDescPtr &descPtr, vxTensorLayout layout, size_t *tensorDims);
 void fillAudioDescriptionPtrFromDims(RpptDescPtr &descPtr, size_t *tensorDims, vxTensorLayout layout = vxTensorLayout::VX_NHW);
 RpptDataType getRpptDataType(vx_enum dataType);
-RpptLayout getRpptLayout(vxTensorLayout layout);
 
 class Kernellist
 {

amd_openvx_extensions/amd_rpp/include/kernels_rpp.h

@@ -149,7 +149,9 @@ extern "C"
         VX_KERNEL_RPP_VIGNETTE = VX_KERNEL_BASE(VX_ID_AMD, VX_LIBRARY_RPP) + 0x72,
         VX_KERNEL_RPP_WARPAFFINE = VX_KERNEL_BASE(VX_ID_AMD, VX_LIBRARY_RPP) + 0x73,
         VX_KERNEL_RPP_PREEMPHASISFILTER = VX_KERNEL_BASE(VX_ID_AMD, VX_LIBRARY_RPP) + 0x74,
-        VX_KERNEL_RPP_SPECTROGRAM = VX_KERNEL_BASE(VX_ID_AMD, VX_LIBRARY_RPP) + 0x75
+        VX_KERNEL_RPP_SPECTROGRAM = VX_KERNEL_BASE(VX_ID_AMD, VX_LIBRARY_RPP) + 0x75,
+        VX_KERNEL_RPP_DOWNMIX = VX_KERNEL_BASE(VX_ID_AMD, VX_LIBRARY_RPP) + 0x76,
+        VX_KERNEL_RPP_TODECIBELS = VX_KERNEL_BASE(VX_ID_AMD, VX_LIBRARY_RPP) + 0x77
     };
 
 #ifdef __cplusplus

amd_openvx_extensions/amd_rpp/include/vx_ext_rpp.h

@@ -1896,6 +1896,31 @@ extern "C"
 	*/
 	SHARED_PUBLIC vx_node VX_API_CALL vxExtRppSpectrogram(vx_graph graph, vx_tensor pSrc, vx_tensor pSrcRoi, vx_tensor pDst, vx_tensor pDstRoi, vx_array windowFunction, vx_scalar centerWindow, vx_scalar reflectPadding, vx_scalar spectrogramLayout, vx_scalar power, vx_scalar nfft, vx_scalar windowLength, vx_scalar windowStep);
 
+	/*! \brief [Graph] Applies downmixing to the input tensor.
+	 * \ingroup group_amd_rpp
+	 * \param [in] graph The handle to the graph.
+	 * \param [in] pSrc The input tensor in <tt>\ref VX_TYPE_FLOAT32</tt> format data.
+	 * \param [out] pDst The output tensor in <tt>\ref VX_TYPE_FLOAT32</tt> format data.
+     * \param [in] pSrcRoi The input tensor of batch size in <tt>unsigned int<tt> containing the roi values for the input.
+	 * \return A node reference <tt>\ref vx_node</tt>. Any possible errors preventing a successful creation should be checked using <tt>\ref vxGetStatus</tt>.
+	 */
+	SHARED_PUBLIC vx_node VX_API_CALL vxExtRppDownmix(vx_graph graph, vx_tensor pSrc, vx_tensor pDst, vx_tensor srcRoi);
+
+	/*! \brief [Graph] Applies to_decibels augmentation to the input tensor.
+	 * \ingroup group_amd_rpp
+	 * \param [in] graph The handle to the graph.
+	 * \param [in] pSrc The input tensor in <tt>\ref VX_TYPE_FLOAT32</tt> format data.
+	 * \param[in] pSrcRoi The input tensor of batch size in <tt>unsigned int<tt> containing the roi values for the input.
+	 * \param [out] pDst The output tensor in <tt>\ref VX_TYPE_FLOAT32</tt> format data.
+	 * \param[in] cutOffDB The input scalar in <tt>\ref VX_TYPE_FLOAT32</tt> format containing  minimum or cut-off ratio in dB
+	 * \param[in] multiplier The input scalar in <tt>\ref VX_TYPE_FLOAT32</tt> format containing factor by which the logarithm is multiplied
+	 * \param[in] referenceMagnitude The input scalar in <tt>\ref VX_TYPE_FLOAT32</tt> format containing Reference magnitude which if not provided uses maximum value of input as reference
+	 * \param [in] inputLayout The input layout in <tt>\ref VX_TYPE_INT32</tt> denotes the layout of input tensor.
+	 * \param [in] outputLayout The output layout in <tt>\ref VX_TYPE_INT32</tt> denotes the layout of output tensor.
+	 * \return A node reference <tt>\ref vx_node</tt>. Any possible errors preventing a successful creation should be checked using <tt>\ref vxGetStatus</tt>.
+	 */
+	SHARED_PUBLIC vx_node VX_API_CALL vxExtRppToDecibels(vx_graph graph, vx_tensor pSrc, vx_tensor pSrcRoi, vx_tensor pDst, vx_scalar cutOffDB, vx_scalar multiplier, vx_scalar referenceMagnitude, vx_scalar inputLayout, vx_scalar outputLayout);
+
 #ifdef __cplusplus
 }
 #endif

amd_openvx_extensions/amd_rpp/source/internal_publishKernels.cpp

@@ -162,6 +162,8 @@ vx_status get_kernels_to_publish()
     STATUS_ERROR_CHECK(ADD_KERNEL(Vignette_Register));
     STATUS_ERROR_CHECK(ADD_KERNEL(WarpAffine_Register));
     STATUS_ERROR_CHECK(ADD_KERNEL(Spectrogram_Register));
+    STATUS_ERROR_CHECK(ADD_KERNEL(Downmix_Register));
+    STATUS_ERROR_CHECK(ADD_KERNEL(ToDecibels_Register));
 
     return status;
 }

amd_openvx_extensions/amd_rpp/source/kernel_rpp.cpp

@@ -2584,6 +2584,43 @@ VX_API_ENTRY vx_node VX_API_CALL vxExtRppSpectrogram(vx_graph graph, vx_tensor p
     return node;
 }
 
+VX_API_ENTRY vx_node VX_API_CALL vxExtRppDownmix(vx_graph graph, vx_tensor pSrc, vx_tensor pDst, vx_tensor pSrcRoi) {
+    vx_node node = NULL;
+    vx_context context = vxGetContext((vx_reference)graph);
+    if (vxGetStatus((vx_reference)context) == VX_SUCCESS) {
+        vx_uint32 devType = getGraphAffinity(graph);
+        vx_scalar deviceType = vxCreateScalar(vxGetContext((vx_reference)graph), VX_TYPE_UINT32, &devType);
+        vx_reference params[] = {
+            (vx_reference)pSrc,
+            (vx_reference)pDst,
+            (vx_reference)pSrcRoi,
+            (vx_reference)deviceType};
+        node = createNode(graph, VX_KERNEL_RPP_DOWNMIX, params, 4);
+    }
+    return node;
+}
+
+VX_API_ENTRY vx_node VX_API_CALL vxExtRppToDecibels(vx_graph graph, vx_tensor pSrc, vx_tensor pSrcRoi, vx_tensor pDst, vx_scalar cutOffDB, vx_scalar multiplier, vx_scalar referenceMagnitude, vx_scalar inputLayout, vx_scalar outputLayout) {
+    vx_node node = NULL;
+    vx_context context = vxGetContext((vx_reference)graph);
+    if (vxGetStatus((vx_reference)context) == VX_SUCCESS) {
+        vx_uint32 devType = getGraphAffinity(graph);
+        vx_scalar deviceType = vxCreateScalar(vxGetContext((vx_reference)graph), VX_TYPE_UINT32, &devType);
+        vx_reference params[] = {
+            (vx_reference)pSrc,
+            (vx_reference)pSrcRoi,
+            (vx_reference)pDst,
+            (vx_reference)cutOffDB,
+            (vx_reference)multiplier,
+            (vx_reference)referenceMagnitude,
+            (vx_reference)inputLayout,
+            (vx_reference)outputLayout,
+            (vx_reference)deviceType};
+        node = createNode(graph, VX_KERNEL_RPP_TODECIBELS, params, 9);
+    }
+    return node;
+}
+
 RpptDataType getRpptDataType(vx_enum vxDataType) {
     switch(vxDataType) {
         case vx_type_e::VX_TYPE_FLOAT32:
@@ -2597,34 +2634,6 @@ RpptDataType getRpptDataType(vx_enum vxDataType) {
     }
 }
 
-RpptLayout getRpptLayout(vxTensorLayout layout) {
-    switch(layout) {
-        case vxTensorLayout::VX_NHWC:
-            return RpptLayout::NHWC;
-        case vxTensorLayout::VX_NCHW:
-            return RpptLayout::NCHW;
-        case vxTensorLayout::VX_NFHWC:
-            return RpptLayout::NHWC;
-        case vxTensorLayout::VX_NFCHW:
-            return RpptLayout::NCHW;
-#if RPP_AUDIO
-        case vxTensorLayout::VX_NHW:
-            return RpptLayout::NHW;
-        case vxTensorLayout::VX_NFT:
-            return RpptLayout::NFT;
-        case vxTensorLayout::VX_NTF:
-            return RpptLayout::NTF;
-#else
-        case vxTensorLayout::VX_NHW:
-        case vxTensorLayout::VX_NFT:
-        case vxTensorLayout::VX_NTF:
-            throw std::runtime_error("RPP_AUDIO flag disabled, Audio layouts are not supported");
-#endif
-        default:
-            throw std::runtime_error("Invalid layout");
-    }
-}
-
 void fillDescriptionPtrfromDims(RpptDescPtr &descPtr, vxTensorLayout layout, size_t *tensorDims) {
     switch(layout) {
         case vxTensorLayout::VX_NHWC: {
@@ -2691,7 +2700,11 @@ void fillAudioDescriptionPtrFromDims(RpptDescPtr &descPtr, size_t *maxTensorDims
     descPtr->strides.wStride = descPtr->c;
     descPtr->strides.cStride = 1;
     descPtr->numDims = 4;
-    descPtr->layout = getRpptLayout(layout);
+    if(tensorLayoutMapping.find(layout) != tensorLayoutMapping.end()) {
+        descPtr->layout = tensorLayoutMapping.at(layout);
+    } else {
+        throw std::runtime_error("Invalid layout");
+    }
 }
 
 // utility functions