The Inference Engine Deep Neural Network Builder API does not support the TensorIterator layer. InferenceEngine::Builder::PriorBoxClustered.InferenceEngine::Builder::Full圜onnected.InferenceEngine::Builder::DetectionOutput.InferenceEngine::Builder::Deconvolution.InferenceEngine::Builder::CTCGreedyDecoder.InferenceEngine::Builder::BatchNormalization.These builders hide all unnecessary methods for the specific layer and add new methods.īelow you can see the list of builders for default layers: Builders for Standard layersĮach default Inference Engine layer has a special builder added in order to simplify the process of layer creation. This class allows you to modify all layer parameters, add new constant data, change type and name of the layer, and create a valid layer object. InferenceEngine::Builder::Layer class creates and modifies layers. The function convertToICNNNetwork(.) converts INetwork to CNNNetwork. This method validates each layer builder and graph structure and creates INetwork. build() allows to generate Inference Engine Network.getLayers() allows to get all layer builders.getLayerConnections(.) allows to get all connections for a layer builder by ID.getLayer(.) allows to get the layer builder from the network builder by ID.disconnect(.) allows to remove connection from the network builder.connect(.) allows to connect two layer builders using layer builder IDs and port indexes.removeLayer(.) allows to remove layer builder from the network builder by ID.This method creates a copy of the original layer builder, puts the copy to the network builder, and returns the ID of the layer builder which was added to the network builder. addLayer(.) allows to add new layer builders to the network builder.Network builder contains the following methods for graph modification: If a graph contains custom layers and shape inference is required, you should add Functions for shape inference to the Network builder from custom Context. All shapes and makes shape inference if it is required.Also the use of this class allows to avoid invalid graphs because it checks: Instead, it creates a copy of the original graph and works with a copied object. This class does not modify the original graph if it is used for graph modification. InferenceEngine::Builder::Network allows to create and modify graphs. This API extends the Inference Engine functionality that allows to create and modify topologies in the source code. Module structure and API itself may be changed in future releases. NOTE: It is a preview version of the Inference Engine Deep Neural Network Builder API for evaluation purpose only.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |