diff options
Diffstat (limited to 'docs/user_guide/operator_list.dox')
-rw-r--r-- | docs/user_guide/operator_list.dox | 36 |
1 files changed, 19 insertions, 17 deletions
diff --git a/docs/user_guide/operator_list.dox b/docs/user_guide/operator_list.dox index fc41265738..05cc892d40 100644 --- a/docs/user_guide/operator_list.dox +++ b/docs/user_guide/operator_list.dox @@ -45,14 +45,14 @@ The main data-types that the Machine Learning functions support are the followin <li>F16: 16-bit half precision floating point <li>S32: 32-bit signed integer <li>U8: 8-bit unsigned char - <li>All: include all above data types + <li>All: Agnostic to any specific data type </ul> Compute Library supports the following data layouts (fast changing dimension from right to left): <ul> <li>NHWC: The native layout of Compute Library that delivers the best performance where channels are in the fastest changing dimension <li>NCHW: Legacy layout where width is in the fastest changing dimension - <li>All: include all above data layouts + <li>All: Agnostic to any specific data layout </ul> where N = batches, C = channels, H = height, W = width @@ -264,7 +264,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">BitwiseAnd - <td rowspan="2" style="width:200px;"> Function to performe bitwise AND between 2 tensors. + <td rowspan="2" style="width:200px;"> Function to perform bitwise AND between 2 tensors. <td rowspan="2"> <ul> <li>ANEURALNETWORKS_LOGICAL_AND @@ -292,7 +292,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">BitwiseNot - <td rowspan="2" style="width:200px;"> Function to performe bitwise NOT. + <td rowspan="2" style="width:200px;"> Function to perform bitwise NOT. <td rowspan="2"> <ul> <li>ANEURALNETWORKS_LOGICAL_NOT @@ -320,7 +320,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">BitwiseOr - <td rowspan="2" style="width:200px;"> Function to performe bitwise OR between 2 tensors. + <td rowspan="2" style="width:200px;"> Function to perform bitwise OR between 2 tensors. <td rowspan="2"> <ul> <li>ANEURALNETWORKS_LOGICAL_OR @@ -348,7 +348,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">BitwiseXor - <td rowspan="2" style="width:200px;"> Function to performe bitwise XOR between 2 tensors. + <td rowspan="2" style="width:200px;"> Function to perform bitwise XOR between 2 tensors. <td rowspan="2"> <ul> <li>n/a @@ -535,7 +535,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">ConvertFullyConnectedWeights - <td rowspan="2" style="width:200px;"> Function to tranpose the wieghts for the fully connected layer. + <td rowspan="2" style="width:200px;"> Function to transpose the weights for the fully connected layer. <td rowspan="2"> <ul> <li>n/a @@ -678,7 +678,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">DeconvolutionLayer - <td rowspan="2" style="width:200px;"> Function to compute a deconvolution or tranpose convolution. + <td rowspan="2" style="width:200px;"> Function to compute a deconvolution or transpose convolution. <td rowspan="2"> <ul> <li>ANEURALNETWORKS_TRANSPOSE_CONV_2D @@ -957,7 +957,7 @@ where N = batches, C = channels, H = height, W = width <tr><td>QASYMM8_SIGNED<td>QSYMM8_PER_CHANNEL<td>S32<td>QASYMM8_SIGNED </table> <tr> - <td rowspan="13">ElementWiseOperations + <td rowspan="13">ElementwiseOperations <td rowspan="13" style="width:200px;"> Function to perform in Cpu: - Div - Max - Min - Pow - SquaredDiff - Comparisons (Equal, greater, greater_equal, less, less_equal, not_equal) Function to perform in CL: - Add - Sub - Div - Max - Min - Pow - SquaredDiff <td rowspan="13"> <ul> @@ -1242,6 +1242,7 @@ where N = batches, C = channels, H = height, W = width <tr><th>src<th>dst <tr><td>F16<td>F16 <tr><td>F32<td>F32 + <tr><td>S32<td>S32 </table> <tr> <td>CLSinLayer @@ -1408,7 +1409,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">FillBorder - <td rowspan="2" style="width:200px;"> Function to . + <td rowspan="2" style="width:200px;"> Function to fill the borders within the XY-planes. <td rowspan="2"> <ul> <li>n/a @@ -1620,7 +1621,7 @@ where N = batches, C = channels, H = height, W = width <tr><td>F16<td>F16<td>F16<td>F16 </table> <tr> - <td rowspan="1">GEMMConv2D + <td rowspan="1">GEMMConv2d <td rowspan="1" style="width:200px;"> General Matrix Multiplication. <td rowspan="1"> <ul> @@ -2193,7 +2194,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">PixelWiseMultiplication - <td rowspan="2" style="width:200px;"> Function to performe a multiplication. + <td rowspan="2" style="width:200px;"> Function to perform a multiplication. <td rowspan="2"> <ul> <li>ANEURALNETWORKS_MUL @@ -2237,11 +2238,12 @@ where N = batches, C = channels, H = height, W = width <tr><td>S16<td>U8<td>S16 <tr><td>S16<td>S16<td>S16 <tr><td>F16<td>F16<td>F16 - <tr><td>F32<td>S32<td>F32 + <tr><td>F32<td>F32<td>F32 + <tr><td>S32<td>S32<td>S32 </table> <tr> <td rowspan="2">PoolingLayer - <td rowspan="2" style="width:200px;"> Function to performe pooling with the specified pooling operation. + <td rowspan="2" style="width:200px;"> Function to perform pooling with the specified pooling operation. <td rowspan="2"> <ul> <li>ANEURALNETWORKS_AVERAGE_POOL_2D @@ -2449,7 +2451,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">ReduceMean - <td rowspan="2" style="width:200px;"> Function to performe reduce mean operation. + <td rowspan="2" style="width:200px;"> Function to perform reduce mean operation. <td rowspan="2"> <ul> <li>ANEURALNETWORKS_MEAN @@ -2483,7 +2485,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="2">ReductionOperation - <td rowspan="2" style="width:200px;"> Function to performe reduce with the following operations - ARG_IDX_MAX: Index of the max value - ARG_IDX_MIN: Index of the min value - MEAN_SUM: Mean of sum - PROD: Product - SUM_SQUARE: Sum of squares - SUM: Sum - MIN: Min - MAX: Max + <td rowspan="2" style="width:200px;"> Function to perform reduce with the following operations - ARG_IDX_MAX: Index of the max value - ARG_IDX_MIN: Index of the min value - MEAN_SUM: Mean of sum - PROD: Product - SUM_SQUARE: Sum of squares - SUM: Sum - MIN: Min - MAX: Max <td rowspan="2"> <ul> <li>ANEURALNETWORKS_REDUCE_ALL @@ -3100,7 +3102,7 @@ where N = batches, C = channels, H = height, W = width </table> <tr> <td rowspan="1">WinogradInputTransform - <td rowspan="1" style="width:200px;"> Function to. + <td rowspan="1" style="width:200px;"> Function to perform a Winograd transform on the input tensor. <td rowspan="1"> <ul> <li>n/a |