Class Conv2d.Options

java.lang.Object
org.tensorflow.op.nn.Conv2d.Options
Enclosing class:
Conv2d<T extends TNumber>
public static class Conv2d.Options extends Object
Optional attributes for Conv2d

  • Method Details

    • useCudnnOnGpu

      public Conv2d.Options useCudnnOnGpu(Boolean useCudnnOnGpu)
      Sets the useCudnnOnGpu option.
      Parameters:
      useCudnnOnGpu - the useCudnnOnGpu option
      Returns:
      this Options instance.

    • explicitPaddings

      public Conv2d.Options explicitPaddings(List<Long> explicitPaddings)
      Sets the explicitPaddings option.
      Parameters:
      explicitPaddings - If padding is "EXPLICIT", the list of explicit padding amounts. For the ith dimension, the amount of padding inserted before and after the dimension is explicit_paddings[2 * i] and explicit_paddings[2 * i + 1], respectively. If padding is not "EXPLICIT", explicit_paddings must be empty.
      Returns:
      this Options instance.

    • explicitPaddings

      public Conv2d.Options explicitPaddings(Long... explicitPaddings)
      Sets the explicitPaddings option.
      Parameters:
      explicitPaddings - If padding is "EXPLICIT", the list of explicit padding amounts. For the ith dimension, the amount of padding inserted before and after the dimension is explicit_paddings[2 * i] and explicit_paddings[2 * i + 1], respectively. If padding is not "EXPLICIT", explicit_paddings must be empty.
      Returns:
      this Options instance.

    • dataFormat

      public Conv2d.Options dataFormat(String dataFormat)
      Sets the dataFormat option.
      Parameters:
      dataFormat - Specify the data format of the input and output data. With the default format "NHWC", the data is stored in the order of: [batch, height, width, channels]. Alternatively, the format could be "NCHW", the data storage order of: [batch, channels, height, width].
      Returns:
      this Options instance.

    • dilations

      public Conv2d.Options dilations(List<Long> dilations)
      Sets the dilations option.
      Parameters:
      dilations - 1-D tensor of length 4. The dilation factor for each dimension of input. If set to k > 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of data_format, see above for details. Dilations in the batch and depth dimensions must be 1.
      Returns:
      this Options instance.

    • dilations

      public Conv2d.Options dilations(Long... dilations)
      Sets the dilations option.
      Parameters:
      dilations - 1-D tensor of length 4. The dilation factor for each dimension of input. If set to k > 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of data_format, see above for details. Dilations in the batch and depth dimensions must be 1.
      Returns:
      this Options instance.