TI Deep Learning Library User Guide
|
This structure define the parameters spatial Pooling layer in TIDL.
Data Fields | |
int32_t | numChannels |
int32_t | poolingType |
int32_t | kernelW |
int32_t | kernelH |
int32_t | strideW |
int32_t | strideH |
int32_t | padW |
int32_t | padH |
int32_t | inDataQ |
int32_t | outDataQ |
int32_t | useCeil |
int32_t sTIDL_PoolingParams_t::numChannels |
Number of channels channels to be processed
int32_t sTIDL_PoolingParams_t::poolingType |
Type of the Pooling as defined in eTIDL_PoolType
int32_t sTIDL_PoolingParams_t::kernelW |
Kernel width
int32_t sTIDL_PoolingParams_t::kernelH |
Kernel height
int32_t sTIDL_PoolingParams_t::strideW |
Stride in horizontal direction
int32_t sTIDL_PoolingParams_t::strideH |
Stride in vertical direction
int32_t sTIDL_PoolingParams_t::padW |
Horizontal Padding requirement in number of elements
int32_t sTIDL_PoolingParams_t::padH |
Vertical Padding requirement in number of elements
int32_t sTIDL_PoolingParams_t::inDataQ |
Q value of the in data
int32_t sTIDL_PoolingParams_t::outDataQ |
Q value expected for out data
int32_t sTIDL_PoolingParams_t::useCeil |
ceil condition for caffe models