///
import { Tensor4D, Tensor5D } from '../tensor';
import { TensorLike } from '../types';
/**
* Computes a 3D convolution over the input x.
*
* @param x The input tensor, of rank 5 or rank 4, of shape
* `[batch, depth, height, width, channels]`. If rank 4,
* batch of 1 is assumed.
* @param filter The filter, rank 5, of shape
* `[filterDepth, filterHeight, filterWidth, inChannels, outChannels]`.
* inChannels must match between input and filter.
* @param strides The strides of the convolution: `[strideDepth, strideHeight,
* strideWidth]`.
* @param pad 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 1x1.
* - For more info, see this guide:
* [https://www.tensorflow.org/api_docs/python/tf/nn/convolution](
* https://www.tensorflow.org/api_docs/python/tf/nn/convolution)
* @param dataFormat: 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.
* @param dilations The dilation rates: `[dilationDepth, dilationHeight,
* dilationWidth]` in which we sample input values across the height
* and width dimensions in atrous convolution. Defaults to `[1, 1, 1]`.
* If `dilations` is a single number, then
* `dilationDepth == dilationHeight == dilationWidth`. If it is greater
* than 1, then all values of `strides` must be 1.
*
* @doc {heading: 'Operations', subheading: 'Convolution'}
*/
declare function conv3d_(x: T | TensorLike, filter: Tensor5D | TensorLike, strides: [number, number, number] | number, pad: 'valid' | 'same', dataFormat?: 'NDHWC' | 'NCDHW', dilations?: [number, number, number] | number): T;
export declare const conv3d: typeof conv3d_;
export {};