Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.13
Performance library for Deep Learning
|
▼C API | |
Engine operations | |
Execution stream operations | |
▼Primitive operations | |
▼Attributes | An extension for controlling primitive behavior |
Sequence of post operations | An extension for performing extra operations after base operation |
Batch Normalization | A primitive to perform batch normalization
|
Common primitive operations | |
Concat | A primitive to concatenate data by arbitrary dimension |
Convolution | A primitive to compute convolution using different algorithms |
Convolution followed by ReLU | A merged primitive to compute a convolution followed by relu |
Eltwise | A primitive to compute element wise operations like parametric rectifier linear unit (ReLU) |
Inner product | A primitive to compute an inner product |
LRN | A primitive to perform local response normalization (LRN) across or within channels |
Memory | A primitive to describe data |
Pooling | A primitive to perform max, min, or average pooling |
ReLU (deprecated, use Eltwise instead) | A primitive to compute a parametric rectifier linear unit (ReLU) |
Reorder | A primitive to copy data between memory formats |
Softmax | A primitive to perform softmax |
Sum | A primitive to sum data |
Service functions | |
▼Types | |
▼Auxiliary types for memory description | |
Operation descriptors | |
Engine | |
Execution stream | |
Generic | |
Primitive | |
Primitive descriptor attributes | |
Primitive descriptor iterators | |
Primitive descriptors | |
Queries | |
▼C++ API | |
Attributes | |
Common data types and enumerations | |
Engine | |
▼Primitives | |
Batch normalization | |
Concat | |
Convolution | |
Eltwise | |
Inner Product | |
LRN | |
Memory | |
Pooling | |
Reorder | |
Softmax | |
Sum | |
View | |
Stream | |
Utils |