A descriptor of a convolution operation. More...
#include <dnnl_types.h>
Collaboration diagram for dnnl_convolution_desc_t:
Public Attributes | |
| dnnl_primitive_kind_t | primitive_kind |
| The kind of primitive. More... | |
| dnnl_prop_kind_t | prop_kind |
| The kind of propagation. More... | |
| dnnl_alg_kind_t | alg_kind |
| The kind of the convolution algorithm. More... | |
| dnnl_memory_desc_t | src_desc |
| Source memory descriptor. | |
| dnnl_memory_desc_t | diff_src_desc |
| Source gradient memory descriptor. | |
| dnnl_memory_desc_t | weights_desc |
| Weights memory descriptor. | |
| dnnl_memory_desc_t | diff_weights_desc |
| Weights gradient memory descriptor. | |
| dnnl_memory_desc_t | bias_desc |
| Bias memory descriptor. | |
| dnnl_memory_desc_t | diff_bias_desc |
| Bias gradient memory descriptor. | |
| dnnl_memory_desc_t | dst_desc |
| Destination memory descriptor. | |
| dnnl_memory_desc_t | diff_dst_desc |
| Destination gradient memory descriptor. | |
| dnnl_dims_t | strides |
| Convolution strides in each spatial dimension. | |
| dnnl_dims_t | dilates |
| Convolution dilates in each spatial dimension. | |
| dnnl_dims_t | padding [2] |
| Padding in each spatial dimension. More... | |
| dnnl_data_type_t | accum_data_type |
| The accumulator data type. Initialized automatically. | |
Detailed Description
A descriptor of a convolution operation.
- Examples:
- cnn_inference_f32.c, and cpu_cnn_training_f32.c.
Member Data Documentation
◆ primitive_kind
| dnnl_primitive_kind_t dnnl_convolution_desc_t::primitive_kind |
The kind of primitive.
Used for self-identifying the primitive descriptor. Must be dnnl_convolution.
◆ prop_kind
| dnnl_prop_kind_t dnnl_convolution_desc_t::prop_kind |
The kind of propagation.
Possible values: dnnl_forward_training, dnnl_forward_inference, dnnl_backward_data, dnnl_backward_weights, and dnnl_backward_bias.
◆ alg_kind
| dnnl_alg_kind_t dnnl_convolution_desc_t::alg_kind |
The kind of the convolution algorithm.
Possible values: dnnl_convolution_direct.
◆ padding
| dnnl_dims_t dnnl_convolution_desc_t::padding[2] |
Padding in each spatial dimension.
padding[0] is a padding in the beginning (padding_l), padding[1] is a padding in the end (padding_r).
The documentation for this struct was generated from the following file:
- include/dnnl_types.h