TI Deep Learning Product User Guide
|
This structure define the parameters CNN/Deep learning net in TIDL.
Data Fields | |
int32_t | netVersion |
int32_t | deviceName |
int32_t | numLayers |
int32_t | weightsElementSize |
int32_t | slopeElementSize |
int32_t | biasElementSize |
int32_t | dataElementSize |
int32_t | interElementSize |
int32_t | quantizationStyle |
int32_t | calibrationOption |
sTIDL_CalibParams_t | calibrationParams |
int32_t | dataFlowInfo |
int32_t | isQuantStatsAvailable |
float32_tidl | preEmptWorstCaseDelay |
int32_t | reserved |
sTIDL_Layer_t | TIDLLayers [TIDL_NUM_MAX_LAYERS] |
int32_t sTIDL_Network_t::netVersion |
Version Number for TIDl net format
int32_t sTIDL_Network_t::deviceName |
Device for which the network has been compiled
int32_t sTIDL_Network_t::numLayers |
Number of layers in the network including the input and output data Layers
int32_t sTIDL_Network_t::weightsElementSize |
Size of compute layer weight parameters in bytes
int32_t sTIDL_Network_t::slopeElementSize |
Size of PRelU layer weight/slope parameters in bytes
int32_t sTIDL_Network_t::biasElementSize |
Size of compute layer Bias parameters in bytes
int32_t sTIDL_Network_t::dataElementSize |
Size of compute layer input and data buffers in bytes
int32_t sTIDL_Network_t::interElementSize |
Size of compute layer intermediate data in bytes
int32_t sTIDL_Network_t::quantizationStyle |
Variable to indicate different types of quantization Styles
int32_t sTIDL_Network_t::calibrationOption |
Variable to indicate different types of calibration options. Please refer eTIDL_CalibOption for various options available. Even though user can try multiple options following options are recommended : 0 : Simple calibration ( Default) 1 : Histogram based activation range collection 7 : Advanced bias calibration
sTIDL_CalibParams_t sTIDL_Network_t::calibrationParams |
Calibration specific parameters, parameters are specific to calibration method and are only applicable if the corresponding option is set by user as part of eTIDL_CalibOption
int32_t sTIDL_Network_t::dataFlowInfo |
dataFlow Info from offline Analysis
int32_t sTIDL_Network_t::isQuantStatsAvailable |
Quantization statistics availability - Updated with tidl_quant_stats_tool
float32_tidl sTIDL_Network_t::preEmptWorstCaseDelay |
It is the WorstCaseDelay in milliSecond for pre-emption for the given network
int32_t sTIDL_Network_t::reserved |
Reserved Parameters
sTIDL_Layer_t sTIDL_Network_t::TIDLLayers[TIDL_NUM_MAX_LAYERS] |
Layer Parameter for each layer