/// <summary>
/// Computes a 2-D convolution given 4-D `input` and `filter` tensors.
///
/// Given an input tensor of shape `[batch, in_height, in_width, in_channels]`
/// and a filter / kernel tensor of shape
/// `[filter_height, filter_width, in_channels, out_channels]`, this op
/// performs the following:
///
/// 1. Flattens the filter to a 2-D matrix with shape
/// `[filter_height * filter_width * in_channels, output_channels]`.
/// 2. Extracts image patches from the input tensor to form a *virtual*
/// tensor of shape `[batch, out_height, out_width,
/// filter_height * filter_width * in_channels]`.
/// 3. For each patch, right-multiplies the filter matrix and the image patch
/// vector.
/// </summary>
/// <param name="parameters"></param>
/// <returns></returns>
public static Tensor conv2d(Conv2dParams parameters)
{
var _op = _op_def_lib._apply_op_helper("Conv2D", name: parameters.Name, args: new
{
input = parameters.Input,
filter = parameters.Filter,
strides = parameters.Strides,
padding = parameters.Padding,
use_cudnn_on_gpu = parameters.UseCudnnOnGpu,
explicit_paddings = parameters.ExplicitPaddings,
data_format = parameters.DataFormat,
dilations = parameters.Dilations
});
return(_op.outputs[0]);
}
public Tensor conv2d(Tensor input, RefVariable filter, int[] strides, string padding, bool use_cudnn_on_gpu = true,
string data_format = "NHWC", int[] dilations = null, string name = null)
{
var parameters = new Conv2dParams
{
Input = input,
Filter = filter,
Strides = strides,
Padding = padding,
UseCudnnOnGpu = use_cudnn_on_gpu,
DataFormat = data_format,
Name = name
};
if (dilations != null)
{
parameters.Dilations = dilations;
}
return(gen_nn_ops.conv2d(parameters));
}
