Class ImageProjectiveTransformV3.Inputs<T extends TNumber>

java.lang.Object
org.tensorflow.op.RawOpInputs<ImageProjectiveTransformV3<T>>
org.tensorflow.op.image.ImageProjectiveTransformV3.Inputs<T>
Enclosing class:
ImageProjectiveTransformV3<T extends TNumber>

public static class ImageProjectiveTransformV3.Inputs<T extends TNumber> extends RawOpInputs<ImageProjectiveTransformV3<T>>
  • Field Details

    • images

      public final Operand<T extends TNumber> images
      4-D with shape [batch, height, width, channels].
    • transforms

      public final Operand<TFloat32> transforms
      2-D Tensor, [batch, 8] or [1, 8] matrix, where each row corresponds to a 3 x 3 projective transformation matrix, with the last entry assumed to be 1. If there is one row, the same transformation will be applied to all images.
    • outputShape

      public final Operand<TInt32> outputShape
      1-D Tensor [new_height, new_width].
    • fillValue

      public final Operand<TFloat32> fillValue
      float, the value to be filled when fill_mode is constant".
    • dtype

      public final DataType dtype
      Input dtype.
    • interpolation

      public final String interpolation
      Interpolation method, "NEAREST" or "BILINEAR".
    • fillMode

      public final String fillMode
      Fill mode, "REFLECT", "WRAP", "CONSTANT", or "NEAREST".
  • Constructor Details