Class Model

Class Documentation

class Model

The Model class is used to define a MindSpore model, facilitating computational graph management.

Public Functions

Status Build(const void *model_data, size_t data_size, ModelType model_type, const std::shared_ptr<Context> &model_context = nullptr)

Build a model from model buffer so that it can run on a device.

Parameters
  • model_data[in] Define the buffer read from a model file.

  • data_size[in] Define bytes number of model buffer.

  • model_type[in] Define The type of model file. Options: ModelType::kMindIR, ModelType::kMindIR_Lite. Only ModelType::kMindIR_Lite is valid for Device-side Inference. Cloud-side Inference supports options ModelType::kMindIR and ModelType::kMindIR_Lite, but option odelType::kMindIR_Lite will be removed in future iterations.

  • model_context[in] Define the context used to store options during execution.

Returns

Status. kSuccess: build success, kLiteModelRebuild: build model repeatedly, Other: other types of errors.

inline Status Build(const std::string &model_path, ModelType model_type, const std::shared_ptr<Context> &model_context = nullptr)

Load and build a model from model buffer so that it can run on a device.

Parameters
  • model_path[in] Define the model path.

  • model_type[in] Define The type of model file. Options: ModelType::kMindIR, ModelType::kMindIR_Lite. Only ModelType::kMindIR_Lite is valid for Device-side Inference. Cloud-side Inference supports options ModelType::kMindIR and ModelType::kMindIR_Lite, but option odelType::kMindIR_Lite will be removed in future iterations.

  • model_context[in] Define the context used to store options during execution.

Returns

Status. kSuccess: build success, kLiteModelRebuild: build model repeatedly, Other: other types of errors.

inline Status Build(const void *model_data, size_t data_size, ModelType model_type, const std::shared_ptr<Context> &model_context, const Key &dec_key, const std::string &dec_mode, const std::string &cropto_lib_path)

Build a model from model buffer so that it can run on a device.

Parameters
  • model_data[in] Define the buffer read from a model file.

  • data_size[in] Define bytes number of model buffer.

  • model_type[in] Define The type of model file. Options: ModelType::kMindIR, ModelType::kMindIR_Lite. Only ModelType::kMindIR_Lite is valid for Device-side Inference. Cloud-side Inference supports options ModelType::kMindIR and ModelType::kMindIR_Lite, but option odelType::kMindIR_Lite will be removed in future iterations.

  • model_context[in] Define the context used to store options during execution.

  • dec_key[in] Define the key used to decrypt the ciphertext model. The key length is 16.

  • dec_mode[in] Define the decryption mode. Options: AES-GCM.

  • cropto_lib_path[in] Define the openssl library path.

Returns

Status. kSuccess: build success, kLiteModelRebuild: build model repeatedly, Other: other types of errors.

inline Status Build(const std::string &model_path, ModelType model_type, const std::shared_ptr<Context> &model_context, const Key &dec_key, const std::string &dec_mode, const std::string &cropto_lib_path)

Load and build a model from model buffer so that it can run on a device.

Parameters
  • model_path[in] Define the model path.

  • model_type[in] Define The type of model file. Options: ModelType::kMindIR, ModelType::kMindIR_Lite. Only ModelType::kMindIR_Lite is valid for Device-side Inference. Cloud-side Inference supports options ModelType::kMindIR and ModelType::kMindIR_Lite, but option odelType::kMindIR_Lite will be removed in future iterations.

  • model_context[in] Define the context used to store options during execution.

  • dec_key[in] Define the key used to decrypt the ciphertext model. The key length is 16.

  • dec_mode[in] Define the decryption mode. Options: AES-GCM.

  • cropto_lib_path[in] Define the openssl library path.

Returns

Status. kSuccess: build success, kLiteModelRebuild: build model repeatedly, Other: other types of errors.

Status Build(GraphCell graph, const std::shared_ptr<Context> &model_context = nullptr, const std::shared_ptr<TrainCfg> &train_cfg = nullptr)

Build a model.

Parameters
  • graph[in] GraphCell is a derivative of Cell. Cell is not available currently. GraphCell can be constructed from Graph, for example, model.Build(GraphCell(graph), context).

  • model_context[in] A context used to store options during execution.

  • train_cfg[in] A config used by training.

Returns

Status.

Status BuildTransferLearning(GraphCell backbone, GraphCell head, const std::shared_ptr<Context> &context, const std::shared_ptr<TrainCfg> &train_cfg = nullptr)

Build a Transfer Learning model where the backbone weights are fixed and the head weights are trainable.

Parameters
  • backbone[in] The static, non-learnable part of the graph

  • head[in] The trainable part of the graph

  • context[in] A context used to store options during execution

  • train_cfg[in] A config used by training

Returns

Status

Status Resize(const std::vector<MSTensor> &inputs, const std::vector<std::vector<int64_t>> &dims)

Resize the shapes of inputs.

Parameters
  • inputs[in] A vector that includes all input tensors in order.

  • dims[in] Defines the new shapes of inputs, should be consistent with inputs.

Returns

Status.

Status UpdateWeights(const std::vector<MSTensor> &new_weights)

Change the size and or content of weight tensors.

Parameters

new_weights[in] a vector of tensors with new shapes and data to use in the model If data pointer is null, the data of the original tensors will be copied to the new ones

Returns

Status.

Status UpdateWeights(const std::vector<std::vector<MSTensor>> &new_weights)

Change the size and or content of weight tensors.

Parameters

new_weights[in] A vector where model constant are arranged in sequence

Returns

Status.

Status Predict(const std::vector<MSTensor> &inputs, std::vector<MSTensor> *outputs, const MSKernelCallBack &before = nullptr, const MSKernelCallBack &after = nullptr)

Inference model API. If use this API in train mode, it's equal to RunStep API.

Parameters
  • inputs[in] A vector where model inputs are arranged in sequence.

  • outputs[out] Which is a pointer to a vector. The model outputs are filled in the container in sequence.

  • before[in] CallBack before predict.

  • after[in] CallBack after predict.

Returns

Status.

Status Predict(const MSKernelCallBack &before = nullptr, const MSKernelCallBack &after = nullptr)

Inference model API. If use this API in train mode, it's equal to RunStep API.

Parameters
  • before[in] CallBack before predict.

  • after[in] CallBack after predict.

Returns

Status.

Status RunStep(const MSKernelCallBack &before = nullptr, const MSKernelCallBack &after = nullptr)

Training API. Run model by step.

Parameters
  • before[in] CallBack before RunStep.

  • after[in] CallBack after RunStep.

Returns

Status.

Status PredictWithPreprocess(const std::vector<std::vector<MSTensor>> &inputs, std::vector<MSTensor> *outputs, const MSKernelCallBack &before = nullptr, const MSKernelCallBack &after = nullptr)

Inference model with preprocess in model.

Parameters
  • inputs[in] A vector where model inputs are arranged in sequence.

  • outputs[out] Which is a pointer to a vector. The model outputs are filled in the container in sequence.

  • before[in] CallBack before predict.

  • after[in] CallBack after predict.

Returns

Status.

Status Preprocess(const std::vector<std::vector<MSTensor>> &inputs, std::vector<MSTensor> *outputs)

Apply data preprocess if it exits in model.

Parameters
  • inputs[in] A vector where model inputs are arranged in sequence.

  • outputs[out] Which is a pointer to a vector. The model outputs are filled in the container in sequence.

Returns

Status.

bool HasPreprocess()

Check if data preprocess exists in model.

Returns

true if data preprocess exists.

inline Status LoadConfig(const std::string &config_path)

Load config file.

Parameters

config_path[in] config file path.

Returns

Status.

inline Status UpdateConfig(const std::string &section, const std::pair<std::string, std::string> &config)

Update config.

Parameters
  • section[in] define the config section.

  • config[in] define the config will be updated.

Returns

Status.

std::vector<MSTensor> GetInputs()

Obtains all input tensors of the model.

Returns

The vector that includes all input tensors.

inline MSTensor GetInputByTensorName(const std::string &tensor_name)

Obtains the input tensor of the model by name.

Returns

The input tensor with the given name, if the name is not found, an invalid tensor is returned.

std::vector<MSTensor> GetGradients() const

Obtain all gradient tensors of the model.

Returns

The vector that includes all gradient tensors.

Status ApplyGradients(const std::vector<MSTensor> &gradients)

Update gradient tensors of the model.

Parameters

gradients[in] A vector new gradients.

Returns

Status of operation

std::vector<MSTensor> GetFeatureMaps() const

Obtain all weights tensors of the model.

Returns

The vector that includes all weights tensors.

std::vector<MSTensor> GetTrainableParams() const

Obtain all trainable parameters of the model optimizers.

Returns

The vector that includes all trainable parameters.

Status UpdateFeatureMaps(const std::vector<MSTensor> &new_weights)

Update weights tensors of the model.

Parameters

new_weights[in] A vector new weights.

Returns

Status of operation

std::vector<MSTensor> GetOptimizerParams() const

Obtain optimizer params tensors of the model.

Returns

The vector that includes all params tensors.

Status SetOptimizerParams(const std::vector<MSTensor> &params)

Update the optimizer parameters.

Parameters

params[in] A vector new optimizer params.

Returns

Status of operation.

Status SetupVirtualBatch(int virtual_batch_multiplier, float lr = -1.0f, float momentum = -1.0f)

Setup training with virtual batches.

Parameters
  • virtual_batch_multiplier[in] - virtual batch multiplier, use any number < 1 to disable.

  • lr[in] - learning rate to use for virtual batch, -1 for internal configuration.

  • momentum[in] - batch norm momentum to use for virtual batch, -1 for internal configuration.

Returns

Status of operation.

Status SetLearningRate(float learning_rate)

Set the Learning Rate of the training.

Parameters

learning_rate[in] to set.

Returns

Status of operation.

float GetLearningRate()

Get the Learning Rate of the optimizer.

Returns

Learning rate. 0.0 if no optimizer was found.

Status InitMetrics(std::vector<Metrics*> metrics)

Initialize object with metrics.

Parameters

metrics[in] A vector of metrics objects.

Returns

0 on success or -1 in case of error

std::vector<Metrics*> GetMetrics()

Accessor to TrainLoop metric objects.

Returns

A vector of metrics

std::vector<MSTensor> GetOutputs()

Obtains all output tensors of the model.

Returns

The vector that includes all output tensors.

inline std::vector<std::string> GetOutputTensorNames()

Obtains names of all output tensors of the model.

Returns

A vector that includes names of all output tensors.

inline MSTensor GetOutputByTensorName(const std::string &tensor_name)

Obtains the output tensor of the model by name.

Returns

The output tensor with the given name, if the name is not found, an invalid tensor is returned.

inline std::vector<MSTensor> GetOutputsByNodeName(const std::string &node_name)

Get output MSTensors of model by node name.

Note

Deprecated, replace with GetOutputByTensorName

Parameters

node_name[in] Define node name.

Returns

The vector of output MSTensor.

Status BindGLTexture2DMemory(const std::map<std::string, unsigned int> &inputGLTexture, std::map<std::string, unsigned int> *outputGLTexture)

Bind GLTexture2D object to cl Memory.

Parameters
  • inputGLTexture[in] The input GLTexture id for Model.

  • outputGLTexture[in] The output GLTexture id for Model.

Returns

Status of operation.

Status SetTrainMode(bool train)

Set the model running mode.

Parameters

train[in] True means model runs in Train Mode, otherwise Eval Mode.

Returns

Status of operation.

bool GetTrainMode() const

Get the model running mode.

Returns

Is Train Mode or not.

Status Train(int epochs, std::shared_ptr<dataset::Dataset> ds, std::vector<TrainCallBack*> cbs)

Performs the training Loop in Train Mode.

Parameters
  • epochs[in] The number of epoch to run.

  • ds[in] A smart pointer to MindData Dataset object.

  • cbs[in] A vector of TrainLoopCallBack objects.

Returns

Status of operation.

Status Evaluate(std::shared_ptr<dataset::Dataset> ds, std::vector<TrainCallBack*> cbs)

Performs the training loop over all data in Eval Mode.

Parameters
  • ds[in] A smart pointer to MindData Dataset object.

  • cbs[in] A vector of TrainLoopCallBack objects.

Returns

Status of operation.

inline std::string GetModelInfo(const std::string &key)

Get model info by key.

Parameters

key[in] The key of model info key-value pair

Returns

The value of the model info associated with the given key.

Public Static Functions

static bool CheckModelSupport(enum DeviceType device_type, ModelType model_type)

Inference model.

Parameters
  • device_type[in] Device type,options are kGPU, kAscend etc.

  • model_type[in] The type of model file, options are ModelType::kMindIR, ModelType::kOM.

Returns

Is supported or not.