Apply 1D conv with un-shared weights.
k_local_conv1d(inputs, kernel, kernel_size, strides, data_format = NULL)3D tensor with shape: (batch_size, steps, input_dim)
the unshared weight for convolution, with shape (output_length, feature_dim, filters)
a list of a single integer, specifying the length of the 1D convolution window
a list of a single integer, specifying the stride length of the convolution
the data format, channels_first or channels_last
the tensor after 1d conv with un-shared weights, with shape (batch_size, output_length, filters)
This function is part of a set of Keras backend functions that enable lower level access to the core operations of the backend tensor engine (e.g. TensorFlow, CNTK, Theano, etc.).
You can see a list of all available backend functions here: https://keras.rstudio.com/articles/backend.html#backend-functions.