Package onnx

Interface OnnxMl.GraphProtoOrBuilder

  • All Superinterfaces:
    org.nd4j.shade.protobuf.MessageLiteOrBuilder, org.nd4j.shade.protobuf.MessageOrBuilder
    All Known Implementing Classes:
    OnnxMl.GraphProto, OnnxMl.GraphProto.Builder
    Enclosing class:
    OnnxMl
    public static interface OnnxMl.GraphProtoOrBuilder
extends org.nd4j.shade.protobuf.MessageOrBuilder

    • Method Detail

      • getNodeList

        List<OnnxMl.NodeProto> getNodeList()
         The nodes in the graph, sorted topologically.
        repeated .onnx.NodeProto node = 1;

      • getNode

        OnnxMl.NodeProto getNode​(int index)
         The nodes in the graph, sorted topologically.
        repeated .onnx.NodeProto node = 1;

      • getNodeCount

        int getNodeCount()
         The nodes in the graph, sorted topologically.
        repeated .onnx.NodeProto node = 1;

      • getNodeOrBuilderList

        List<? extends OnnxMl.NodeProtoOrBuilder> getNodeOrBuilderList()
         The nodes in the graph, sorted topologically.
        repeated .onnx.NodeProto node = 1;

      • getNodeOrBuilder

        OnnxMl.NodeProtoOrBuilder getNodeOrBuilder​(int index)
         The nodes in the graph, sorted topologically.
        repeated .onnx.NodeProto node = 1;

      • getName

        String getName()
         The name of the graph.
        string name = 2;
        Returns:
        The name.

      • getNameBytes

        org.nd4j.shade.protobuf.ByteString getNameBytes()
         The name of the graph.
        string name = 2;
        Returns:
        The bytes for name.

      • getInitializerList

        List<OnnxMl.TensorProto> getInitializerList()
         A list of named tensor values, used to specify constant inputs of the graph.
 Each initializer (both TensorProto as well SparseTensorProto) MUST have a name.
 The name MUST be unique across both initializer and sparse_initializer,
 but the name MAY also appear in the input list.
        repeated .onnx.TensorProto initializer = 5;

      • getInitializer

        OnnxMl.TensorProto getInitializer​(int index)
         A list of named tensor values, used to specify constant inputs of the graph.
 Each initializer (both TensorProto as well SparseTensorProto) MUST have a name.
 The name MUST be unique across both initializer and sparse_initializer,
 but the name MAY also appear in the input list.
        repeated .onnx.TensorProto initializer = 5;

      • getInitializerCount

        int getInitializerCount()
         A list of named tensor values, used to specify constant inputs of the graph.
 Each initializer (both TensorProto as well SparseTensorProto) MUST have a name.
 The name MUST be unique across both initializer and sparse_initializer,
 but the name MAY also appear in the input list.
        repeated .onnx.TensorProto initializer = 5;

      • getInitializerOrBuilderList

        List<? extends OnnxMl.TensorProtoOrBuilder> getInitializerOrBuilderList()
         A list of named tensor values, used to specify constant inputs of the graph.
 Each initializer (both TensorProto as well SparseTensorProto) MUST have a name.
 The name MUST be unique across both initializer and sparse_initializer,
 but the name MAY also appear in the input list.
        repeated .onnx.TensorProto initializer = 5;

      • getInitializerOrBuilder

        OnnxMl.TensorProtoOrBuilder getInitializerOrBuilder​(int index)
         A list of named tensor values, used to specify constant inputs of the graph.
 Each initializer (both TensorProto as well SparseTensorProto) MUST have a name.
 The name MUST be unique across both initializer and sparse_initializer,
 but the name MAY also appear in the input list.
        repeated .onnx.TensorProto initializer = 5;

      • getSparseInitializerList

        List<OnnxMl.SparseTensorProto> getSparseInitializerList()
         Initializers (see above) stored in sparse format.
        repeated .onnx.SparseTensorProto sparse_initializer = 15;

      • getSparseInitializer

        OnnxMl.SparseTensorProto getSparseInitializer​(int index)
         Initializers (see above) stored in sparse format.
        repeated .onnx.SparseTensorProto sparse_initializer = 15;

      • getSparseInitializerCount

        int getSparseInitializerCount()
         Initializers (see above) stored in sparse format.
        repeated .onnx.SparseTensorProto sparse_initializer = 15;

      • getSparseInitializerOrBuilderList

        List<? extends OnnxMl.SparseTensorProtoOrBuilder> getSparseInitializerOrBuilderList()
         Initializers (see above) stored in sparse format.
        repeated .onnx.SparseTensorProto sparse_initializer = 15;

      • getSparseInitializerOrBuilder

        OnnxMl.SparseTensorProtoOrBuilder getSparseInitializerOrBuilder​(int index)
         Initializers (see above) stored in sparse format.
        repeated .onnx.SparseTensorProto sparse_initializer = 15;

      • getDocString

        String getDocString()
         A human-readable documentation for this graph. Markdown is allowed.
        string doc_string = 10;
        Returns:
        The docString.

      • getDocStringBytes

        org.nd4j.shade.protobuf.ByteString getDocStringBytes()
         A human-readable documentation for this graph. Markdown is allowed.
        string doc_string = 10;
        Returns:
        The bytes for docString.

      • getInputList

        List<OnnxMl.ValueInfoProto> getInputList()
         The inputs and outputs of the graph.
        repeated .onnx.ValueInfoProto input = 11;

      • getInput

        OnnxMl.ValueInfoProto getInput​(int index)
         The inputs and outputs of the graph.
        repeated .onnx.ValueInfoProto input = 11;

      • getInputCount

        int getInputCount()
         The inputs and outputs of the graph.
        repeated .onnx.ValueInfoProto input = 11;

      • getInputOrBuilderList

        List<? extends OnnxMl.ValueInfoProtoOrBuilder> getInputOrBuilderList()
         The inputs and outputs of the graph.
        repeated .onnx.ValueInfoProto input = 11;

      • getInputOrBuilder

        OnnxMl.ValueInfoProtoOrBuilder getInputOrBuilder​(int index)
         The inputs and outputs of the graph.
        repeated .onnx.ValueInfoProto input = 11;

      • getOutputCount

        int getOutputCount()
        repeated .onnx.ValueInfoProto output = 12;

      • getValueInfoList

        List<OnnxMl.ValueInfoProto> getValueInfoList()
         Information for the values in the graph. The ValueInfoProto.name's
 must be distinct. It is optional for a value to appear in value_info list.
        repeated .onnx.ValueInfoProto value_info = 13;

      • getValueInfo

        OnnxMl.ValueInfoProto getValueInfo​(int index)
         Information for the values in the graph. The ValueInfoProto.name's
 must be distinct. It is optional for a value to appear in value_info list.
        repeated .onnx.ValueInfoProto value_info = 13;

      • getValueInfoCount

        int getValueInfoCount()
         Information for the values in the graph. The ValueInfoProto.name's
 must be distinct. It is optional for a value to appear in value_info list.
        repeated .onnx.ValueInfoProto value_info = 13;

      • getValueInfoOrBuilderList

        List<? extends OnnxMl.ValueInfoProtoOrBuilder> getValueInfoOrBuilderList()
         Information for the values in the graph. The ValueInfoProto.name's
 must be distinct. It is optional for a value to appear in value_info list.
        repeated .onnx.ValueInfoProto value_info = 13;

      • getValueInfoOrBuilder

        OnnxMl.ValueInfoProtoOrBuilder getValueInfoOrBuilder​(int index)
         Information for the values in the graph. The ValueInfoProto.name's
 must be distinct. It is optional for a value to appear in value_info list.
        repeated .onnx.ValueInfoProto value_info = 13;

      • getQuantizationAnnotationList

        List<OnnxMl.TensorAnnotation> getQuantizationAnnotationList()
         This field carries information to indicate the mapping among a tensor and its
 quantization parameter tensors. For example:
 For tensor 'a', it may have {'SCALE_TENSOR', 'a_scale'} and {'ZERO_POINT_TENSOR', 'a_zero_point'} annotated,
 which means, tensor 'a_scale' and tensor 'a_zero_point' are scale and zero point of tensor 'a' in the model.
        repeated .onnx.TensorAnnotation quantization_annotation = 14;

      • getQuantizationAnnotation

        OnnxMl.TensorAnnotation getQuantizationAnnotation​(int index)
         This field carries information to indicate the mapping among a tensor and its
 quantization parameter tensors. For example:
 For tensor 'a', it may have {'SCALE_TENSOR', 'a_scale'} and {'ZERO_POINT_TENSOR', 'a_zero_point'} annotated,
 which means, tensor 'a_scale' and tensor 'a_zero_point' are scale and zero point of tensor 'a' in the model.
        repeated .onnx.TensorAnnotation quantization_annotation = 14;

      • getQuantizationAnnotationCount

        int getQuantizationAnnotationCount()
         This field carries information to indicate the mapping among a tensor and its
 quantization parameter tensors. For example:
 For tensor 'a', it may have {'SCALE_TENSOR', 'a_scale'} and {'ZERO_POINT_TENSOR', 'a_zero_point'} annotated,
 which means, tensor 'a_scale' and tensor 'a_zero_point' are scale and zero point of tensor 'a' in the model.
        repeated .onnx.TensorAnnotation quantization_annotation = 14;

      • getQuantizationAnnotationOrBuilderList

        List<? extends OnnxMl.TensorAnnotationOrBuilder> getQuantizationAnnotationOrBuilderList()
         This field carries information to indicate the mapping among a tensor and its
 quantization parameter tensors. For example:
 For tensor 'a', it may have {'SCALE_TENSOR', 'a_scale'} and {'ZERO_POINT_TENSOR', 'a_zero_point'} annotated,
 which means, tensor 'a_scale' and tensor 'a_zero_point' are scale and zero point of tensor 'a' in the model.
        repeated .onnx.TensorAnnotation quantization_annotation = 14;

      • getQuantizationAnnotationOrBuilder

        OnnxMl.TensorAnnotationOrBuilder getQuantizationAnnotationOrBuilder​(int index)
         This field carries information to indicate the mapping among a tensor and its
 quantization parameter tensors. For example:
 For tensor 'a', it may have {'SCALE_TENSOR', 'a_scale'} and {'ZERO_POINT_TENSOR', 'a_zero_point'} annotated,
 which means, tensor 'a_scale' and tensor 'a_zero_point' are scale and zero point of tensor 'a' in the model.
        repeated .onnx.TensorAnnotation quantization_annotation = 14;