Weight update (user-managed memory)

// 1. Initialize resources.
aclInit(nullptr);
aclrtSetDevice(0);

// 2. Query the memory information of the model built based on the graph building API. The model contains the inference graph, weight initialization graph, and weight update graph. The model file name bundle.om is used as an example.
aclmdlBundleQueryInfo *query_info = aclmdlBundleCreateQueryInfo();
aclmdlBundleQueryInfoFromFile("./bundle.om", query_info);

// 3. Obtain the total number of graphs and memory information in the model based on the query result.
size_t modelNum = 0;
aclmdlBundleGetQueryModelNum(query_info, &modelNum);
// (Optional) Obtain the refreshable weight required by the model and allocate the memory. If the memory is not allocated, the memory is allocated by the system.
size_t variableWeightSize = 0;
aclmdlBundleGetVarWeightSize(query_info, &variableWeightSize);
void *var_p = nullptr;
aclrtMalloc(&var_p, variableWeightSize, ACL_MEM_MALLOC_NORMAL_ONLY);
//Assume that modelNum is set to 3. The input parameters of the aclgrphBundleBuildModel API are three graphs with fixed IDs, which are 0, 1, and 2.
// (Optional) Obtain and allocate the working memory and weight memory required by the inference graph whose index is 0. If the memory is not allocated, the allocation is completed by the system.
size_t inferWorkSize, inferConstWeightSize;
aclmdlBundleGetSize(query_info, 0, &inferWorkSize, &inferConstWeightSize);
void *inferWorkPtr = nullptr;
aclrtMalloc(&inferWorkPtr, inferWorkSize, ACL_MEM_MALLOC_NORMAL_ONLY);
void *inferConstWeightPtr = nullptr;
aclrtMalloc(&inferConstWeightPtr, inferConstWeightSize, ACL_MEM_MALLOC_NORMAL_ONLY);

// 4. Initialize bundle.om.
uint32_t bundle_id = 0;
// If the memory is allocated by the system, set var_p to nullptr and variableWeightSize to 0.
aclmdlBundleInitFromFile("./bundle.om", var_p, variableWeightSize, &bundle_id);

// 5. Load the graph based on the index.
uint32_t infer_id= 0;
// If the memory is allocated internally by the system, the value is aclmdlBundleLoadModelWithMem(bundle_id, 0, nullptr, 0, nullptr, 0, &init_id).
aclmdlBundleLoadModelWithMem(bundle_id, 0, inferWorkPtr, inferWorkSize,inferConstWeightPtr, inferConstWeightSize, &infer_id);
uint32_t init_id= 0;
aclmdlBundleLoadModelWithMem(bundle_id, 1, nullptr, 0, nullptr, 0, &init_id);
uint32_t update_id= 0;
aclmdlBundleLoadModelWithMem(bundle_id, 2, nullptr, 0, nullptr, 0, &update_id);

//If the weight does not need to be updated, execute the weight initialization graph and inference graph.
// 6. Execute the weight initialization graph. For details about how to prepare the model input and output, see the sample code in "Other Inference Features" under "Model Inference."
aclmdlExecute(init_id, init_mdl_input, init_mdl_output);

// 7. Execute the inference graph. For details about how to prepare the model input and output, see the sample code in other inference features of model inference.
aclmdlExecute(infer_id, infer_mdl_input, infer_mdl_output);

// If a weight needs to be updated, update the weight before executing the inference graph.
// 8. Execute the weight update graph.
// If a weight does not need to be updated, for example, the 0th weight, the shape can be passed as an empty tensor, but the device memory must be valid.
size_t no_need_refresh_index = 0;
std::vector<int64_t> dims{0};
// If the elements in the dims array are 0, the tensor is empty.
auto tensorDesc = aclCreateTensorDesc(ACL_FLOAT, dims.size(), dims.data(), ACL_FORMAT_ND);
aclmdlSetDatasetTensorDesc(update_mdl_input, tensorDesc, no_need_refresh_index);

// 9. If a weight needs to be updated, the first weight is used as an example.
size_t need_refresh_index = 1;
std::vector<int64_t> dims{1, 3, 224, 224};
auto tensorDesc = aclCreateTensorDesc(ACL_FLOAT, dims.size(), dims.data(), ACL_FORMAT_ND);
aclmdlSetDatasetTensorDesc(update_mdl_input, tensorDesc, need_refresh_index);

// 10. Execute the weight update graph. For details about how to prepare the model input and output, see the sample code in other inference features of model inference.
aclmdlExecute(update_id, update_mdl_input, update_mdl_output);

// 11. Execute the inference graph. For details about how to prepare the model input and output, see the sample code in other inference features of model inference.
aclmdlExecute(infer_id, infer_mdl_input, infer_mdl_output);

// 12. Unload the model.
aclmdlBundleUnloadModel(bundle_id, infer_id);
aclmdlBundleUnloadModel(bundle_id, init_id);
aclmdlBundleUnloadModel(bundle_id, update_id);
aclmdlBundleUnload(bundle_id);

// 13. Release resources.
aclrtResetDevice(0);
aclFinalize();