rml_op_type
Operations supported by Radeon ML.
API
Graph Manipulation
Items
Name |
Value |
Brief Explanation |
---|---|---|
RML_OP_UNSPECIFIED |
0 |
Unspecified operation type. |
RML_OP_ABS |
1010 |
Calculates absolute of an input tensor, element-wise.
|
RML_OP_ACOS |
1020 |
Calculates arccosine of an input tensor, element-wise.
|
RML_OP_ADD |
1030 |
Sums input tensors up, element-wise.
|
RML_OP_ASIN |
1050 |
Calculates arcsine of an input tensor, element-wise.
|
RML_OP_ATAN |
1070 |
Calculates arctangent of an input tensor, element-wise.
|
RML_OP_AVG |
1080 |
Calculates average between input tensors, element-wise.
|
RML_OP_BATCH_NORM |
1090 |
Performs batch normalization of an input tensor.
|
RML_OP_BIAS_ADD |
1100 |
Adds bias to an input tensor.
|
RML_OP_CAST |
1110 |
Casts elements of an input tensor to a specified type.
|
RML_OP_CEIL |
1120 |
Ceils elements of an input tensor.
|
RML_OP_CELU |
1130 |
Applies CeLU activation to an input tensor, element-wise.
|
RML_OP_CLIP |
1140 |
Limits input tensor values within a specified range.
|
RML_OP_CONCAT |
1150 |
Concatenates input tensors into a single tensor along a specified axis.
|
RML_OP_CONST |
1160 |
Stores specified tensor data.
|
RML_OP_CONV_2D |
1190 |
Performs 2D convolution of an input tensor.
|
RML_OP_CONV_2D_DEPTHWISE |
1200 |
Performs depthwise 2D convolution of an input tensor.
|
RML_OP_CONV_2D_TRANSPOSE |
1210 |
Performs transposed 2D convolution of an input tensor.
|
RML_OP_COS |
1240 |
Calculates cosine of an input tensor, element-wise.
|
RML_OP_DEPTH_TO_SPACE |
1250 |
Rearranges input tensor data from channels into blocks of spatial data.
|
RML_OP_DIV |
1270 |
Divides input tensors, element-wise.
|
RML_OP_ELU |
1300 |
Applies ELU activation to an input tensor, element-wise.
|
RML_OP_EXP |
1310 |
Calculates exponent of an input tensor, element-wise.
|
RML_OP_FLATTEN |
1330 |
Flattens an input tensor into a 2D matrix.
|
RML_OP_FLOOR |
1340 |
Floors elements of an input tensor.
|
RML_OP_GEMM |
1360 |
Calculates gemm of input tensors, element-wise.
|
RML_OP_IDENTITY |
1380 |
Identity operator.
|
RML_OP_LEAKY_RELU |
1390 |
Applies Leaky ReLU activation to an input tensor, element-wise.
|
RML_OP_LOCAL_RESPONSE_NORM |
1410 |
Performs local response normalization of an input tensor.
|
RML_OP_LOG_SOFTMAX |
1420 |
Calculates LogSoftMax of an input tensor, element-wise.
|
RML_OP_LOGN |
1430 |
Calculates natural logarithm of an input tensor, element-wise.
|
RML_OP_MAX |
1440 |
Calculates maximum of input tensors, element-wise.
|
RML_OP_MIN |
1450 |
Calculates minimum of input tensors, element-wise.
|
RML_OP_MUL |
1460 |
Multiplies input tensors, element-wise.
|
RML_OP_NEG |
1470 |
Calculates neg of the input tensor, element-wise.
|
RML_OP_PAD |
1490 |
Describes a data reorganization operator that inflates the input tensor with zeroes (or some other value) on the edges
|
RML_OP_PARAMETRIC_RELU |
1510 |
Performs Parametric ReLU activation of an input tensor, elsement-wise.
|
RML_OP_PLACEHOLDER |
1520 |
Special operation that holds information about input data.
|
RML_OP_POOL_2D_AVG |
1560 |
Performs 2D average pooling of an input tensor.
|
RML_OP_POOL_2D_GLOBAL_AVG |
1570 |
Performs 2D global average pooling of an input tensor.
|
RML_OP_POOL_2D_MAX |
1580 |
Performs 2D max pooling of an input tensor.
|
RML_OP_PORT |
1625 |
Returns a specified output tensor of an input operation.
|
RML_OP_POW |
1630 |
Calculates power of an input tensor, element-wise.
|
RML_OP_QUANTIZE_LINEAR |
1640 |
Transforms a hig-precision input tensor into a low-precision output tensor.
|
RML_OP_RECIP |
1650 |
Calculates reciprocal of an input tensor, element-wise.
|
RML_OP_REDUCE_ADD |
1660 |
Calculates sum of the input tensor elements along provided axes.
|
RML_OP_REDUCE_ADD_SQUARE |
1670 |
Calculates sum square of input tensor elements along provided axes.
|
RML_OP_REDUCE_ARGMAX |
1680 |
Calculates maximum elements indices of input tensor elements along provided axis.
|
RML_OP_REDUCE_ARGMIN |
1690 |
Calculates minimum elements indices of input tensor elements along provided axis.
|
RML_OP_REDUCE_AVG |
1700 |
Calculates average of input tensor elements along provided axes.
|
RML_OP_REDUCE_L1 |
1710 |
Calculates L1 norm of input tensor elements along provided axes.
|
RML_OP_REDUCE_L2 |
1720 |
Calculates L2 norm of input tensor elements along provided axes.
|
RML_OP_REDUCE_LOGN_ADD |
1730 |
Calculates log sum of input tensor elements along provided axes.
|
RML_OP_REDUCE_LOGN_ADD_EXP |
1740 |
Calculates log sum exponent of input tensor element along provided axes.
|
RML_OP_REDUCE_MAX |
1750 |
Calculates maximum of input tensor elements along provided axes.
|
RML_OP_REDUCE_MIN |
1760 |
Calculates minimum of input tensor elements along provided axes.
|
RML_OP_REDUCE_MUL |
1770 |
Calculates product of input tensor elements along provided axes.
|
RML_OP_RELU |
1780 |
Applies ReLU activation to an input tensor, element-wise.
|
RML_OP_RELU6 |
1790 |
Applies ReLU6 activation to an input tensor, element-wise.
|
RML_OP_RESHAPE |
1800 |
Changes the shape of an input tensor without changing tensor data.
|
RML_OP_RESIZE_2D_NEAREST |
1810 |
Resizes an input tensor along spatial dims using the nearest neighbor algorithm.
|
RML_OP_RESIZE_2D_BICUBIC |
1820 |
Resizes an input tensor along spatial dims using the bicubic algorithm.
|
RML_OP_RSQRT |
1870 |
Calculates reciprocal of square root of an input tensor, element-wise.
|
RML_OP_SELU |
1880 |
Applies Scaled ELU activation to an input tensor, element-wise.
|
RML_OP_SHAPE |
1890 |
Outputs the shape of an input tensor.
|
RML_OP_SIGMOID |
1900 |
Applies Sigmoid activation of the input tensor, element-wise.
|
RML_OP_SIN |
1910 |
Calculates sine of an input tensor, element-wise.
|
RML_OP_SLICE |
1920 |
Produces a strided slice of an input tensor along multiple axes.
|
RML_OP_SOFTMAX |
1930 |
Applies Softmax activation to an input tensor, element-wise.
|
RML_OP_SOFTPLUS |
1950 |
Applies Softplus activation to an input tensor, element-wise.
|
RML_OP_SOFTSIGN |
1960 |
Applies Softsign activation to an input tensor, element-wise.
|
RML_OP_SPACE_TO_DEPTH |
1970 |
Rearranges blocks of spatial tensor data into channels.
|
RML_OP_SQRT |
1990 |
Calculates square root of an input tensor, element-wise.
|
RML_OP_SQUEEZE |
2000 |
Removes single-dimensional entries from the shape of a tensor.
|
RML_OP_STACK |
2010 |
Stacks a list of tensors with rank R into single tensor with rank R+1.
|
RML_OP_SUB |
2020 |
Subtracts input tensors, element-wise.
|
RML_OP_TAN |
2030 |
Calculate tangent of the input tensor, element-wise.
|
RML_OP_TANH |
2040 |
Applies hyperbolic tangent activation to an input tensor, element-wise.
|
RML_OP_THRESHOLDED_RELU |
2050 |
Applies Thresholded ReLU activation of the input tensor, element-wise.
|
RML_OP_TOP_K |
2060 |
Retrieve the top-K largest or smallest elements along a specified axis.
|
RML_OP_TRANSPOSE |
2070 |
Transposes an input tensor.
|
RML_OP_UNSQUEEZE |
2080 |
Inserts dimensions of size 1 at specified axis indices.
|