Function computeConv2DInfo

  • computeConv2DInfo(inShape, filterShape, strides, dilations, pad, roundingMode?, depthwise?, dataFormat?): Conv2DInfo

  • Computes the information for a forward pass of a convolution/pooling operation.

    Parameters

    • inShape: [number, number, number, number]
    • filterShape: [number, number, number, number]
    • strides: number | [number, number]
    • dilations: number | [number, number]
    • pad: number | "same" | "valid" | ExplicitPadding
    • Optional roundingMode: "floor" | "round" | "ceil"
    • Optional depthwise: boolean
    • Optional dataFormat: "channelsFirst" | "channelsLast"

    Returns Conv2DInfo

Settings

Member Visibility

Theme

Generated using TypeDoc