Lines Matching refs:model
51 * Gets the supported operations in a model.
62 * @param model A model whose operations--and their corresponding operands--
68 * - INVALID_ARGUMENT if provided model is invalid
74 getSupportedOperations_1_3(Model model)
78 * Asynchronously creates a prepared model for execution and optionally
82 * alternative representations to a model for execution, possibly including
83 * transformations on the constant data, optimization on the model's graph,
84 * or compilation into the device's native binary format. The model itself
88 * the prepared model to cache files for faster model compilation time when
89 * the same model preparation is requested in the future. There are two
90 * types of cache file handles provided to the driver: model cache and data
101 * The model is prepared asynchronously with respect to the caller. The
103 * function related to preparing the model (as opposed to saving the
104 * prepared model to cache) are correct. If there is an error, prepareModel
108 * to preparing the model are valid and there is no error, prepareModel must
109 * launch an asynchronous task to prepare the model in the background, and
115 * When the asynchronous task has finished preparing the model, it must
117 * prepareModel. If the model was prepared successfully, the callback object
119 * produced IPreparedModel object. If an error occurred preparing the model,
123 * The model is prepared with a priority. This priority is relative to other
128 * prepareModel_1_3 can be called with an optional deadline. If the model
129 * is not able to be prepared before the provided deadline, the model
143 * Optionally, the driver may save the prepared model to cache during the
145 * not affect the status of preparing the model. Even if the input arguments
147 * cache, the prepareModel function must finish preparing the model. The
151 * The only information that may be unknown to the model at this stage is
154 * the prepared model may only be finished when it is paired with a set of
155 * inputs to the model. Note that the same prepared model object may be used
159 * Multiple threads may call prepareModel on the same model concurrently.
161 * @param model The model to be prepared for execution.
163 * model.
164 * @param priority The priority of the prepared model relative to other
166 * @param deadline The time by which the model is expected to be prepared.
167 * If the model cannot be prepared by the deadline, the preparation may
184 * identifying the prepared model. The same token will be provided when
185 * retrieving the prepared model from the cache files with
193 * preparing the model for execution and the prepared model if
195 * must be called exactly once, even if the model could not be prepared.
196 * @return status Error status of launching a task which prepares the model
202 * the model is invalid
203 * - MISSED_DEADLINE_* if the preparation is aborted because the model
207 prepareModel_1_3(Model model, ExecutionPreference preference,
215 * Creates a prepared model from cache files for execution.
217 * prepareModelFromCache_1_3 is used to retrieve a prepared model directly from
218 * cache files to avoid slow model compilation time. There are
219 * two types of cache file handles provided to the driver: model cache
230 * The model is prepared asynchronously with respect to the caller. The
240 * asynchronous task to prepare the model in the background, and immediately return
246 * When the asynchronous task has finished preparing the model, it must
248 * prepareModelFromCache_1_3. If the model was prepared successfully, the
251 * the model, the callback object must be invoked with the appropriate
255 * model is not able to prepared before the provided deadline, the model
270 * The only information that may be unknown to the model at this stage is
273 * the prepared model may only be finished when it is paired with a set of
274 * inputs to the model. Note that the same prepared model object may be
278 * @param deadline The time by which the model is expected to be prepared.
279 * If the model cannot be prepared by the deadline, the preparation may
290 * identifying the prepared model. It is the same token provided when saving
296 * preparing the model for execution and the prepared model if
298 * must be called exactly once, even if the model could not be prepared.
299 * @return status Error status of launching a task which prepares the model
306 * - MISSED_DEADLINE_* if the preparation is aborted because the model
335 * dimensions of the corresponding model operands of the input and output roles. The dimensions
348 * @param inputRoles A vector of roles with each specifying an input to a prepared model.
349 * @param outputRoles A vector of roles with each specifying an output to a prepared model.
351 * model operands of the roles must have the same OperandType, scale, zero point, and