Main Content

transposedConv1dLayer

Transposed 1-D convolution layer

Since R2022a

    Description

    A transposed 1-D convolution layer upsamples one-dimensional feature maps.

    This layer is sometimes incorrectly known as a "deconvolution" or "deconv" layer. This layer is the transpose of convolution and does not perform deconvolution.

    layer = transposedConv1dLayer(filterSize,numFilters) returns a 1-D transposed convolution layer and sets the FilterSize and NumFilters properties.

    example

    layer = transposedConv1dLayer(filterSize,numFilters,Name=Value) returns a 1-D transposed convolutional layer and specifies additional options using one or more name-value arguments.

    Examples

    collapse all

    Create a 1-D transposed convolutional layer with 96 filters of length 11 and a stride of 4.

    layer = transposedConv1dLayer(11,96,Stride=4)
    layer = 
      TransposedConvolution1DLayer with properties:
    
                Name: ''
    
       Hyperparameters
          FilterSize: 11
         NumChannels: 'auto'
          NumFilters: 96
              Stride: 4
        CroppingMode: 'manual'
        CroppingSize: [0 0]
    
       Learnable Parameters
             Weights: []
                Bias: []
    
    Use properties method to see a list of all properties.
    
    

    Input Arguments

    collapse all

    Length of the filters, specified as a positive integer. The filter size defines the size of the local regions to which the neurons connect in the input.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    Number of filters, specified as a positive integer. This number corresponds to the number of neurons in the layer that connect to the same region in the input. This parameter determines the number of channels (feature maps) in the output of the layer.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    Name-Value Arguments

    Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

    Example: transposedConv1dLayer(11,96,Stride=4) creates a 1-D transposed convolutional layer with 96 filters of length 11 and a stride of 4.

    Transposed Convolution

    collapse all

    Upsampling factor of the input, specified as a positive integer that corresponds to the horizontal stride.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    Output size reduction, specified as one of the following:

    • "same" — Set the cropping so that the output size equals inputSize.*Stride, where inputSize is the length of the layer input. If Cropping is "same", then the software automatically sets the CroppingMode property of the layer to 'same'.

      The software trims an equal amount from the left and right, when possible. If the horizontal crop amount has an odd value, then the software trims an extra column from the right.

    • A positive integer — Crop the specified amount of data from the left and right edges.

    • A vector of nonnegative integers [l r] — Crop l and r from the left and right, respectively.

    If you set the Cropping option to a numeric value, then the software automatically sets the CroppingMode property of the layer to 'manual'.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | char | string

    Number of input channels, specified as one of the following:

    • "auto" — Automatically determine the number of input channels at training time.

    • Positive integer — Configure the layer for the specified number of input channels. NumChannels and the number of channels in the layer input data must match. For example, if the input is an RGB image, then NumChannels must be 3. If the input is the output of a convolutional layer with 16 filters, then NumChannels must be 16.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | char | string

    Parameters and Initialization

    collapse all

    Function to initialize the weights, specified as one of the following:

    • 'glorot' — Initialize the weights with the Glorot initializer [1] (also known as the Xavier initializer). The Glorot initializer independently samples from a uniform distribution with a mean of zero and a variance of 2/(numIn + numOut), where numIn = FilterSize*NumChannels and numOut = FilterSize*NumFilters.

    • 'he' – Initialize the weights with the He initializer [2]. The He initializer samples from a normal distribution with a mean of zero and a variance of 2/numIn, where numIn = FilterSize*NumChannels.

    • 'narrow-normal' — Initialize the weights by independently sampling from a normal distribution with a mean of zero and a standard deviation of 0.01.

    • 'zeros' — Initialize the weights with zeros.

    • 'ones' — Initialize the weights with ones.

    • Function handle — Initialize the weights with a custom function. If you specify a function handle, then the function must be of the form weights = func(sz), where sz is the size of the weights. For an example, see Specify Custom Weight Initialization Function.

    The layer only initializes the weights when the Weights property is empty.

    Data Types: char | string | function_handle

    Function to initialize the biases, specified as one of these values:

    • "zeros" — Initialize the biases with zeros.

    • "ones" — Initialize the biases with ones.

    • "narrow-normal" — Initialize the biases by independently sampling from a normal distribution with a mean of zero and a standard deviation of 0.01.

    • Function handle — Initialize the biases with a custom function. If you specify a function handle, then the function must have the form bias = func(sz), where sz is the size of the biases.

    The layer initializes the biases only when the Bias property is empty.

    Data Types: char | string | function_handle

    Layer weights for the transposed convolution operation, specified as a FilterSize-by-NumFilters-by-NumChannels numeric array or [].

    The layer weights are learnable parameters. You can specify the initial value of the weights directly using the Weights property of the layer. When you train a network, if the Weights property of the layer is nonempty, then the trainnet and trainNetwork functions use the Weights property as the initial value. If the Weights property is empty, then the software uses the initializer specified by the WeightsInitializer property of the layer.

    Data Types: single | double

    Layer biases for the transposed convolutional operation, specified as a 1-by-NumFilters numeric array or [].

    The layer biases are learnable parameters. When you train a neural network, if Bias is nonempty, then the trainnet and trainNetwork functions use the Bias property as the initial value. If Bias is empty, then software uses the initializer specified by BiasInitializer.

    Data Types: single | double

    Learning Rate and Regularization

    collapse all

    Learning rate factor for the weights, specified as a nonnegative scalar.

    The software multiplies this factor by the global learning rate to determine the learning rate for the weights in this layer. For example, if WeightLearnRateFactor is 2, then the learning rate for the weights in this layer is twice the current global learning rate. The software determines the global learning rate based on the settings you specify using the trainingOptions function.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    Learning rate factor for the biases, specified as a nonnegative scalar.

    The software multiplies this factor by the global learning rate to determine the learning rate for the biases in this layer. For example, if BiasLearnRateFactor is 2, then the learning rate for the biases in the layer is twice the current global learning rate. The software determines the global learning rate based on the settings you specify using the trainingOptions function.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    L2 regularization factor for the weights, specified as a nonnegative scalar.

    The software multiplies this factor by the global L2 regularization factor to determine the L2 regularization for the weights in this layer. For example, if WeightL2Factor is 2, then the L2 regularization for the weights in this layer is twice the global L2 regularization factor. You can specify the global L2 regularization factor using the trainingOptions function.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    L2 regularization factor for the biases, specified as a nonnegative scalar.

    The software multiplies this factor by the global L2 regularization factor to determine the L2 regularization for the biases in this layer. For example, if BiasL2Factor is 2, then the L2 regularization for the biases in this layer is twice the global L2 regularization factor. The software determines the global L2 regularization factor based on the settings you specify using the trainingOptions function.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    Layer

    collapse all

    Layer name, specified as a character vector or a string scalar. For Layer array input, the trainnet and dlnetwork functions automatically assign names to layers with the name "".

    The transposedConv1dLayer object stores this property as a character vector.

    Data Types: char | string

    Output Arguments

    collapse all

    Transposed 1-D convolution layer, returned as a TransposedConvolution1DLayer object.

    Algorithms

    collapse all

    1-D Transposed Convolutional Layer

    A transposed 1-D convolution layer upsamples one-dimensional feature maps.

    The standard convolution operation downsamples the input by applying sliding convolutional filters to the input. By flattening the input and output, you can express the convolution operation as Y=CX+B for the convolution matrix C and bias vector B that can be derived from the layer weights and biases.

    Similarly, the transposed convolution operation upsamples the input by applying sliding convolutional filters to the input. To upsample the input instead of downsampling using sliding filters, the layer zero-pads each edge of the input with padding that has the size of the corresponding filter edge size minus 1.

    By flattening the input and output, the transposed convolution operation is equivalent to Y=CX+B, where C and B denote the convolution matrix and bias vector for standard convolution derived from the layer weights and biases, respectively. This operation is equivalent to the backward function of a standard convolution layer.

    A 1-D transposed convolution layer upsamples a single dimension only. The dimension that the layer upsamples depends on the layer input:

    • For time series and vector sequence input (data with three dimensions corresponding to the channels, observations, and time steps), the layer upsamples the time dimension.

    • For 1-D image input (data with three dimensions corresponding to the spatial pixels, channels, and observations), the layer upsamples the spatial dimension.

    • For 1-D image sequence input (data with four dimensions corresponding to the spatial pixels, channels, observations, and time steps), the layer upsamples the spatial dimension.

    Layer Input and Output Formats

    Layers in a layer array or layer graph pass data to subsequent layers as formatted dlarray objects. The format of a dlarray object is a string of characters, in which each character describes the corresponding dimension of the data. The formats consist of one or more of these characters:

    • "S" — Spatial

    • "C" — Channel

    • "B" — Batch

    • "T" — Time

    • "U" — Unspecified

    For example, 2-D image data that is represented as a 4-D array, where the first two dimensions correspond to the spatial dimensions of the images, the third dimension corresponds to the channels of the images, and the fourth dimension corresponds to the batch dimension, can be described as having the format "SSCB" (spatial, spatial, channel, batch).

    You can interact with these dlarray objects in automatic differentiation workflows such as developing a custom layer, using a functionLayer object, or using the forward and predict functions with dlnetwork objects.

    This table shows the supported input formats of TransposedConvolution1DLayer objects and the corresponding output format. If the output of the layer is passed to a custom layer that does not inherit from the nnet.layer.Formattable class, or a FunctionLayer object with the Formattable property set to 0 (false), then the layer receives an unformatted dlarray object with dimensions ordered corresponding to the formats in this table.

    Input FormatOutput Format

    "SCB" (spatial, channel, batch)

    "SCB" (spatial, channel, batch)

    "CBT" (channel, batch, time)

    "CBT" (channel, batch, time)

    "SCBT" (spatial, channel, batch, time)

    "SCBT" (spatial, channel, batch, time)

    In dlnetwork objects, TransposedConvolution1DLayer objects also support these input and output format combinations.

    Input FormatOutput Format

    "SC" (spatial, channel)

    "SC" (spatial, channel)

    "CT" (channel, time)

    "CT" (channel, time)

    "SCT" (spatial, channel, time)

    "SCT" (spatial, channel, time)

    References

    [1] Glorot, Xavier, and Yoshua Bengio. "Understanding the Difficulty of Training Deep Feedforward Neural Networks." In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 249–356. Sardinia, Italy: AISTATS, 2010. https://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf

    [2] He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification." In 2015 IEEE International Conference on Computer Vision (ICCV), 1026–34. Santiago, Chile: IEEE, 2015. https://doi.org/10.1109/ICCV.2015.123

    Version History

    Introduced in R2022a