- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 15 for MetaGraphDef (0.13 sec)
-
tensorflow/compiler/mlir/tensorflow/translate/import_model.h
public: SavedModelMLIRImportInput(const MetaGraphDef* meta_graph_def, const GraphDebugInfo& debug_info) : meta_graph_def_(meta_graph_def), debug_info_(debug_info) { DCHECK(meta_graph_def); } virtual ~SavedModelMLIRImportInput(); // The original MetaGraphDef of the savedmodel. const MetaGraphDef& meta_graph_def() const { return *meta_graph_def_; }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 01 11:17:36 UTC 2024 - 6.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/py_function_lib.h
// exported model is produced. It is used to copy the asset files to // `dst_saved_model_path`. `tags` will be attached to the saved // `MetaGraphDef`. `signature_def_map` will be passed to the // `add_meta_graph_and_variables` function, which is internally used to add a // `MetaGraphDef` to save to the SavedModel. // // Returns `true` if successful. Returns `std::nullopt` otherwise. //
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Apr 09 06:33:29 UTC 2024 - 5.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/cc/saved_model_import.h
// Loads a SavedModel at `saved_model_path` and converts it to `mlir::ModuleOp`. // // `tags` identify the `tensorflow::MetaGraphDef` to load from the SavedModel. // Similarly, `signature_keys` identify the functions (`SignatureDef`s) to load // within the `MetaGraphDef`. `ctx` is the `MLIRContext`, which should outlive // the returned `ModuleOp`, thus marked with the lifetime bound attribute.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 12:49:45 UTC 2024 - 4.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/py_function_lib.py
the representative dataset for the actual data provided for inference. Args: model_dir: Path to SavedModel directory. tags: Collection of tags identifying the MetaGraphDef within the SavedModel. representative_dataset_map: A map where signature keys are mapped to corresponding representative datasets. Raises:
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 31 05:32:11 UTC 2024 - 27.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/cc/calibration/component.h
// Function alias mapping for pre-calibrated SavedModel. Used to preserve // aliased functions. absl::flat_hash_map<FunctionName, FunctionAlias> function_aliases_; // Tags to identify the MetaGraphDef to load from a SavedModel. const std::unordered_set<std::string> tags_; const absl::flat_hash_map<std::string, tensorflow::SignatureDef> signature_def_map_;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 14 06:31:57 UTC 2024 - 5.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/cc/saved_model_import.cc
} absl::StatusOr<absl::flat_hash_map<FunctionName, FunctionAlias>> GetFunctionAliases(absl::string_view saved_model_path, const std::unordered_set<std::string>& tags) { tensorflow::MetaGraphDef meta_graph; TF_RETURN_IF_ERROR(tensorflow::ReadMetaGraphDefFromSavedModel( saved_model_path, tags, &meta_graph)); absl::flat_hash_map<FunctionName, FunctionAlias> function_aliases(
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 12:49:45 UTC 2024 - 6.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/quantization_config.proto
message WeightOnlyPtqPreset {} // Metadata specific to the input TensorFlow SavedModel, which may be required // to identify the specific MetaGraphDef to quantize, for example. // Next ID: 2 message TfSavedModelConfig { // Set of tags that uniquely identify the `MetaGraphDef` existing in the // input SavedModel. repeated string tags = 1; } // Configures the graph transformation pipeline for quantization.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 14.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/translate/tf_mlir_translate.cc
absl::string_view saved_model_dir, const std::unordered_set<std::string>& tags, absl::Span<std::string> exported_names, mlir::MLIRContext* context, MLIRImportOptions options) { MetaGraphDef meta_graph_def; auto status = ReadMetaGraphDefFromSavedModel(saved_model_dir, tags, &meta_graph_def); if (!status.ok()) { LOG(ERROR) << "Failed to load saved model v1 '" << saved_model_dir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 07 11:51:44 UTC 2024 - 14.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/save_model.py
Args: saved_model_path: Path to the saved model. signature_keys: List of keys identifying SignatureDef to retrieve. If None, retrieve all except the init signature. tags: Set of tags identifying the MetaGraphDef within the SavedModel. Returns: A map from signature_key to its SignatureDef. """ if tags is None: tags = {tag_constants.SERVING} loader = saved_model_loader.SavedModelLoader(saved_model_path)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 01:09:50 UTC 2024 - 12.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/quantize_model.py
Returns: A SavedModel object with TF quantization applied. Raises: ValueError: when representative_dataset is not provided for non-QAT model. RuntimeError: When a MetaGraphDef could not be found associated with `tags` in the SavedModel. """ logging.info( 'Running static range quantization on model: %s', src_saved_model_path )
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 34.2K bytes - Viewed (0)