Vanilla RNN descriptor backward propagation primitive. More...
#include <dnnl.hpp>
Collaboration diagram for dnnl::vanilla_rnn_backward::desc:
Public Member Functions | |
| desc (prop_kind prop_kind, algorithm activation, rnn_direction direction, const memory::desc &src_layer_desc, const memory::desc &src_iter_desc, const memory::desc &weights_layer_desc, const memory::desc &weights_iter_desc, const memory::desc &bias_desc, const memory::desc &dst_layer_desc, const memory::desc &dst_iter_desc, const memory::desc &diff_src_layer_desc, const memory::desc &diff_src_iter_desc, const memory::desc &diff_weights_layer_desc, const memory::desc &diff_weights_iter_desc, const memory::desc &diff_bias_desc, const memory::desc &diff_dst_layer_desc, const memory::desc &diff_dst_iter_desc, rnn_flags flags=rnn_flags::undef, float alpha=0.0f, float beta=0.0f) | |
| Constructs a descriptor for a vanilla RNN backward propagation primitive. More... | |
Detailed Description
Vanilla RNN descriptor backward propagation primitive.
Constructor & Destructor Documentation
◆ desc()
|
inline |
Constructs a descriptor for a vanilla RNN backward propagation primitive.
The src_iter_desc together with diff_src_iter_desc, bias_desc together with diff_bias_desc, and dst_iter_desc together with diff_src_iter_desc, may point to a zero memory descriptor. This would then indicate that the RNN backward propagation primitive should not use the respective data and should use zero values instead.
- Note
- All memory descriptors can be initialized with dnnl::memory::format_tag::any value of
format_tag.
Inputs:
- src_layer (dnnl::primitive_desc_base::src_desc (0))
- src_iter (dnnl::primitive_desc_base::src_desc (1)), if used
- weights_layer (dnnl::primitive_desc_base::weights_desc (0))
- weights_iter (dnnl::primitive_desc_base::weights_desc (1))
- bias (dnnl::primitive_desc_base::weights_desc (2)), if used
- dst_layer (dnnl::primitive_desc_base::dst_desc (0))
- dst_iter (dnnl::primitive_desc_base::dst_desc (1)), if used
- diff_dst_layer (dnnl::primitive_desc_base::diff_dst_desc (0))
- diff_dst_iter (dnnl::primitive_desc_base::diff_dst_desc (1)), if used
- workspace (dnnl::primitive_desc_base::workspace_desc (0))
Outputs:
- diff_src_layer (dnnl::primitive_desc_base::diff_src_desc (0))
- diff_src_iter (dnnl::primitive_desc_base::diff_src_desc (1)), if used
- diff_weights_layer (dnnl::primitive_desc_base::diff_weights_desc (0))
- diff_weights_iter (dnnl::primitive_desc_base::diff_weights_desc (1))
- diff_bias (dnnl::primitive_desc_base::diff_weights_desc (2)), if used
- Parameters
-
prop_kind Propagation kind. Must be dnnl::prop_kind::backward. activation Activation kind. Possible values are dnnl::algorithm::eltwise_relu, dnnl::algorithm::eltwise_tanh, or dnnl::algorithm::eltwise_logistic. direction RNN direction. See dnnl::rnn_direction for more info. src_layer_desc Memory descriptor for the input vector. src_iter_desc Memory descriptor for the input recurrent hidden state vector. weights_layer_desc Memory descriptor for the weights applied to the layer input. weights_iter_desc Memory descriptor for the weights applied to the recurrent input. bias_desc Bias memory descriptor. dst_layer_desc Memory descriptor for the output vector. dst_iter_desc Memory descriptor for the output recurrent hidden state vector. diff_src_layer_desc Memory descriptor for the diff of input vector. diff_src_iter_desc Memory descriptor for the diff of input recurrent hidden state vector. diff_weights_layer_desc Memory descriptor for the diff of weights applied to the layer input. diff_weights_iter_desc Memory descriptor for the diff of weights applied to the recurrent input. diff_bias_desc Diff bias memory descriptor. diff_dst_layer_desc Memory descriptor for the diff of output vector. diff_dst_iter_desc Memory descriptor for the diff of output recurrent hidden state vector. flags Unused. alpha Negative slope if activation is dnnl::algorithm::eltwise_relu. beta Unused.
The documentation for this struct was generated from the following file:
- include/dnnl.hpp