Caffe2 - C++ API
A deep learning, cross platform ML framework
Data Fields
caffe2::Int8ConvDNNLowPPackedWeightBlob Struct Reference

Packed weight matrix for DNNLOWP Int8Conv operator. More...

#include <fbgemm_pack_blob.h>

Inheritance diagram for caffe2::Int8ConvDNNLowPPackedWeightBlob:

Data Fields

std::shared_ptr< fbgemm::Packed3x3ConvMatrix > W_depthwise_3x3
std::shared_ptr< fbgemm::Packed3x3x3ConvMatrix > W_depthwise_3x3x3
std::shared_ptr< fbgemm::PackWeightMatrixForGConv< std::int8_t > > W_gconv
- Data Fields inherited from caffe2::Int8FCDNNLowPPackedWeightBlob
std::vector< dnnlowp::TensorQuantizationParams > qparams
std::shared_ptr< std::vector< std::int32_t > > column_offsets
Tensor original_tensor {CPU}
std::shared_ptr< std::vector< std::int32_t > > bias
std::shared_ptr< fbgemm::PackBMatrix< std::int8_t > > W
std::shared_ptr< fbgemm::PackBMatrix< std::int8_t, std::int16_t > > W_acc16
std::shared_ptr< fbgemm::CompressedSparseColumn > W_outlier
int nbits_in_non_outlier

Detailed Description

Packed weight matrix for DNNLOWP Int8Conv operator.

Definition at line 38 of file fbgemm_pack_blob.h.

The documentation for this struct was generated from the following file: