Function holoscan::utils::get_data_per_model

gxf_result_t holoscan::utils::get_data_per_model(InputContext &op_input, const std::vector<std::string> &in_tensors, HoloInfer::DataMap &data_per_input_tensor, std::map<std::string, std::vector<int>> &dims_per_tensor, bool cuda_buffer_out, const std::string &module, gxf_context_t &context, CudaStreamHandler &cuda_stream_handler)

Extracts data from GXF Receivers.

Parameters
  • op_input – Input context

  • in_tensors – Input tensor names

  • data_per_input_tensorMap is updated with output tensor name as key mapped to data buffer

  • dims_per_tensorMap is updated with tensor name as key mapped to dimension of input tensor

  • cuda_buffer_out – Flag defining the location of output memory (Device or Host)

  • module – Module that called for data extraction

  • context – GXF execution context

  • cuda_stream_handler – Cuda steam handler

Returns

GXF result code

© Copyright 2022-2023, NVIDIA. Last updated on Sep 13, 2023.