|
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.17
Performance library for Deep Learning
|
Description of tensor of packed weights for rnn. More...
#include <mkldnn_types.h>
Public Attributes | |
| mkldnn_rnn_packed_memory_format_t | format |
| int | n_parts |
| int | n |
| int | parts [MKLDNN_RNN_MAX_N_PARTS] |
| size_t | part_pack_size [MKLDNN_RNN_MAX_N_PARTS] |
| size_t | offset_compensation |
| size_t | size |
Description of tensor of packed weights for rnn.
| mkldnn_rnn_packed_memory_format_t mkldnn_rnn_packed_desc_t::format |
| int mkldnn_rnn_packed_desc_t::n_parts |
| int mkldnn_rnn_packed_desc_t::n |
| int mkldnn_rnn_packed_desc_t::parts[MKLDNN_RNN_MAX_N_PARTS] |
| size_t mkldnn_rnn_packed_desc_t::part_pack_size[MKLDNN_RNN_MAX_N_PARTS] |
| size_t mkldnn_rnn_packed_desc_t::offset_compensation |
| size_t mkldnn_rnn_packed_desc_t::size |
1.8.13