#模型推理应用开发指导

#include <iostream>
#include "hobot/dnn/hb_dnn.h"
#include "hobot/hb_ucp.h"
#include "hobot/hb_ucp_sys.h"

int main(int argc, char **argv) {
  // Step 1: Load the model
  hbDNNPackedHandle_t packed_dnn_handle;
  const char* model_file_name= "./mobilenetv1/mobilenetv1_224x224_nv12.hbm";
  hbDNNInitializeFromFiles(&packed_dnn_handle, &model_file_name, 1);

  // Step 2: Get model names
  const char **model_name_list;
  int model_count = 0;
  hbDNNGetModelNameList(&model_name_list, &model_count, packed_dnn_handle);

  // Step 3: Get dnn_handle
  hbDNNHandle_t dnn_handle;
  hbDNNGetModelHandle(&dnn_handle, packed_dnn_handle, model_name_list[0]);

  // Step 4: Prepare input data
  int input_count = 0;
  hbDNNGetInputCount(&input_count, dnn_handle);
  std::vector<hbDNNTensor> input(input_count);
  for (int i = 0; i < input_count; i++) {
    hbDNNGetInputTensorProperties(&input[i].properties, dnn_handle, i);
    auto &mem = input[i].sysMem;
    /*
      1. For dynamic input, you need to set the corresponding dynamic parameters in input[i].properties.
      2. Call hbUCPMalloc/hbUCPMallocCached to apply for the corresponding memory size based on the model input.
         such as hbUCPMallocCached(&mem, size, 0);
      3. Determine whether the input needs quantization or padding based on properties, then fill the input data into mem.
      4. If the memory is a cacheable, you must actively perform a flush operation after writing.
         such as hbUCPMemFlush(&mem, HB_SYS_MEM_CACHE_CLEAN); 
    */
  }

  // Step 5: Prepare storage space for the output data of the model
  int output_count = 0;
  hbDNNGetOutputCount(&output_count, dnn_handle);
  std::vector<hbDNNTensor> output(output_count);
  for (int i = 0; i < output_count; i++) {
    hbDNNTensorProperties &output_properties = output[i].properties;
    hbDNNGetOutputTensorProperties(&output_properties, dnn_handle, i);
    int out_aligned_size = output_properties.alignedByteSize;
    hbUCPSysMem &mem = output[i].sysMem;
    hbUCPMallocCached(&mem, out_aligned_size, 0);
  }

  // Step 6: Create the asynchronous inference task
  hbUCPTaskHandle_t task_handle{nullptr};
  hbDNNInferV2(&task_handle,
               output.data(),
               input.data(),
               dnn_handle);

  // Step 7: Submit the task
  hbUCPSchedParam infer_sched_param;
  HB_UCP_INITIALIZE_SCHED_PARAM(&infer_sched_param);
  hbUCPSubmitTask(task_handle, &infer_sched_param);

  // Step 8: Wait for the task to end
  hbUCPWaitTaskDone(task_handle, 0);

  // Step 9: Parse model output, here we take the classification model as an example to get the top1 result
  for (int i = 0; i < output_count; i++) {
    // For output memory that applies for the cacheable attribute, it needs to be actively flushed before reading.
    hbUCPMemFlush(&(output[i].sysMem), HB_SYS_MEM_CACHE_INVALIDATE);

    /*
       1. Determine whether the output data has padding, whether inverse quantization is required, and the quantization parameter information required for inverse quantization, etc.
       2. parsing process.
    */
  }

  // Release the task
  hbUCPReleaseTask(task_handle);

  // Release the memory
  for (int i = 0; i < input_count; i++) {
    hbUCPFree(&(input[i].sysMem));
  }
  for (int i = 0; i < output_count; i++) {
    hbUCPFree(&(output[i].sysMem));
  }

  // Release the model
  hbDNNRelease(packed_dnn_handle);

  return 0;
}