Function maxPool3d

maxPool3d<T>(x, filterSize, strides, pad, dimRoundingMode?, dataFormat?): T
Computes the 3D max pooling.
```
const x = tf.tensor5d([1, 2, 3, 4, 5, 6, 7, 8], [1, 2, 2, 2, 1]);
const result = tf.maxPool3d(x, 2, 1, 'valid');
result.print();
```
Type Parameters
- T extends Tensor4D | Tensor5D
Parameters
- x: TensorLike | T
  The input tensor, of rank 5 or rank 4 of shape [batch, depth, height, width, inChannels].
- filterSize: number | [number, number, number]
  The filter size: [filterDepth, filterHeight, filterWidth]. If filterSize is a single number, then filterDepth == filterHeight == filterWidth.
- strides: number | [number, number, number]
  The strides of the pooling: [strideDepth, strideHeight, strideWidth]. If strides is a single number, then strideDepth == strideHeight == strideWidth.
- pad: number | "same" | "valid"
  The type of padding algorithm.
  - same and stride 1: output will be of same size as input, regardless of filter size.
  - valid: output will be smaller than input if filter is larger than 1*1x1.
  - For more info, see this guide: https://www.tensorflow.org/api_docs/python/tf/nn/convolution
- Optional dimRoundingMode: "floor" | "round" | "ceil"
  A string from: 'ceil', 'round', 'floor'. If none is provided, it will default to truncate.
- Optional dataFormat: "NDHWC" | "NCDHW"
  An optional string from: "NDHWC", "NCDHW". Defaults to "NDHWC". Specify the data format of the input and output data. With the default format "NDHWC", the data is stored in the order of: [batch, depth, height, width, channels]. Only "NDHWC" is currently supported.
Returns T
Doc
- Defined in src/node_modules/@tensorflow/tfjs-node-gpu/node_modules/@tensorflow/tfjs-core/dist/ops/max_pool_3d.d.ts:55

Generated using TypeDoc