NVIDIA DeepStream SDK API Reference6.1.1 Release |
tensor meta containing prepared tensor and related info inside preprocess user meta which is attached at batch level
Definition at line 50 of file nvdspreprocess_meta.h.
Data Fields | |
void * | raw_tensor_buffer |
raw tensor buffer preprocessed for infer More... | |
guint64 | buffer_size |
size of raw tensor buffer More... | |
std::vector< int > | tensor_shape |
raw tensor buffer shape More... | |
NvDsDataType | data_type |
model datatype for which tensor prepared More... | |
std::string | tensor_name |
to be same as model input layer name More... | |
guint | gpu_id |
gpu-id on which tensor prepared More... | |
void * | private_data |
pointer to buffer from tensor pool More... | |