tf.compat.v1.nn.conv1d

View source on GitHub

Computes a 1-D convolution of input with rank >=3 and a 3-D filter. (deprecated argument values) (deprecated argument values)

tf.compat.v1.nn.conv1d(
    value=None, filters=None, stride=None, padding=None, use_cudnn_on_gpu=None,
    data_format=None, name=None, input=None, dilations=None
)

Given an input tensor of shape batch_shape + [in_width, in_channels] if data_format is "NWC", or batch_shape + [in_channels, in_width] if data_format is "NCW", and a filter / kernel tensor of shape [filter_width, in_channels, out_channels], this op reshapes the arguments to pass them to conv2d to perform the equivalent convolution operation.

Internally, this op reshapes the input tensors and invokes tf.nn.conv2d. For example, if data_format does not start with "NC", a tensor of shape batch_shape + [in_width, in_channels] is reshaped to batch_shape + [1, in_width, in_channels], and the filter is reshaped to [1, filter_width, in_channels, out_channels]. The result is then reshaped back to batch_shape + [out_width, out_channels] (where out_width is a function of the stride and padding as in conv2d) and returned to the caller.