|
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.17
Performance library for Deep Learning
|
Modules | |
| Common primitive operations | |
| Attributes | |
| An extension for controlling primitive behavior. | |
| Memory | |
| A primitive to describe and store data. | |
| Reorder | |
| A primitive to copy data between memory formats. | |
| Concat | |
| A primitive to concatenate data by arbitrary dimension. | |
| Sum | |
| A primitive to sum data. | |
| Convolution | |
| A primitive to compute convolution using different algorithms. | |
| Deconvolution | |
| A primitive to compute deconvolution using different algorithms. | |
| Shuffle | |
| A primitive to shuffle data along the axis. | |
| Eltwise | |
| A primitive to compute element wise operations like parametric rectifier linear unit (ReLU). | |
| Softmax | |
| A primitive to perform softmax. | |
| Pooling | |
| A primitive to perform max or average pooling. | |
| LRN | |
| A primitive to perform local response normalization (LRN) across or within channels. | |
| Batch Normalization | |
| A primitive to perform batch normalization. | |
| Inner product | |
| A primitive to compute an inner product. | |
| RNN | |
| A primitive to compute common recurrent layer. | |
1.8.13