Main Content

coder.getDeepLearningLayers

Get convolutional neural network layers supported for code generation for a specific deep learning library

Description

example

coder.getDeepLearningLayers(libraryname) returns the convolutional neural network layers supported for code generation for a specific deep learning library.

Note

To use coder.getDeepLearningLayers, you must install the support package that corresponds to libraryname:

  • For 'arm-compute' and 'mkldnn', install MATLAB® Coder™ Interface for Deep Learning Libraries.

  • For 'cudnn', 'tensorrt' or 'arm-compute-mali', install GPU Coder™ Interface for Deep Learning Libraries.

Note

The coder.getDeepLearningLayers function does not list certain custom layers if the associated support packages are not installed. For example, keras layers are not listed if the Deep Learning Toolbox™ Importer for TensorFlow™-Keras Models support package is not installed.

Examples

collapse all

Get a list of layers supported for code generation for Intel® Math Kernel Library for Deep Neural Networks.

coder.getDeepLearningLayers('mkldnn')
ans =

  48×1 cell array

    {'AdditionLayer'                               }
    {'AnchorBoxLayer'                              }
    {'AveragePooling2DLayer'                       }
    {'BatchNormalizationLayer'                     }
    {'BiLSTMLayer'                                 }
    {'ClassificationOutputLayer'                   }
    {'ClippedReLULayer'                            }
    {'ConcatenationLayer'                          }
    {'Convolution2DLayer'                          }
    {'Crop2DLayer'                                 }
    {'CrossChannelNormalizationLayer'              }
    {'DepthConcatenationLayer'                     }
    {'DropoutLayer'                                }
    {'ELULayer'                                    }
    {'FocalLossLayer'                              }
    {'FullyConnectedLayer'                         }
    {'GlobalAveragePooling2DLayer'                 }
    {'GlobalMaxPooling2DLayer'                     }
    {'GroupedConvolution2DLayer'                   }
    {'ImageInputLayer'                             }
    {'LSTMLayer'                                   }
    {'LeakyReLULayer'                              }
    {'MaxPooling2DLayer'                           }
    {'MaxUnpooling2DLayer'                         }
    {'PixelClassificationLayer'                    }
    {'RCNNBoxRegressionLayer'                      }
    {'ReLULayer'                                   }
    {'RegressionOutputLayer'                       }
    {'SSDMergeLayer'                               }
    {'SequenceInputLayer'                          }
    {'SigmoidLayer'                                }
    {'SoftmaxLayer'                                }
    {'SpaceToDepthLayer'                           }
    {'TanhLayer'                                   }
    {'TransposedConvolution2DLayer'                }
    {'WordEmbeddingLayer'                          }
    {'YOLOv2OutputLayer'                           }
    {'YOLOv2ReorgLayer'                            }
    {'YOLOv2TransformLayer'                        }
    {'nnet.keras.layer.FlattenCStyleLayer'         }
    {'nnet.keras.layer.GlobalAveragePooling2dLayer'}
    {'nnet.keras.layer.SigmoidLayer'               }
    {'nnet.keras.layer.TanhLayer'                  }
    {'nnet.keras.layer.ZeroPadding2dLayer'         }
    {'nnet.onnx.layer.ElementwiseAffineLayer'      }
    {'nnet.onnx.layer.FlattenLayer'                }
    {'nnet.onnx.layer.IdentityLayer'               }
    {'ScalingLayer'                                }

Input Arguments

collapse all

Name of deep learning library, specified as one of the values in this table.

ValueDescription
'arm-compute'

ARM® Compute Library for targeting ARM CPU processors.

Requires the MATLAB Coder Interface for Deep Learning Libraries.

'arm-compute-mali'

ARM Compute Library for targeting ARM GPU processors.

Requires the GPU Coder product and the GPU Coder Interface for Deep Learning Libraries.

'cudnn'

cuDNN library.

Requires the GPU Coder product and the GPU Coder Interface for Deep Learning Libraries.

'mkldnn'

Intel Math Kernel Library for Deep Neural Networks.

Requires the MATLAB Coder Interface for Deep Learning Libraries.

'tensorrt'

TensorRT™ library.

Requires the GPU Coder product and the GPU Coder Interface for Deep Learning Libraries.

Introduced in R2018b