Apply 2D conv with un-shared weights.
k_local_conv2d(inputs, kernel, kernel_size, strides, output_shape,
data_format = NULL)4D tensor with shape: (batch_size, filters, new_rows, new_cols) if data_format='channels_first' or 4D tensor with shape: (batch_size, new_rows, new_cols, filters) if data_format='channels_last'.
the unshared weight for convolution, with shape (output_items, feature_dim, filters)
a list of 2 integers, specifying the width and height of the 2D convolution window.
a list of 2 integers, specifying the strides of the convolution along the width and height.
a list with (output_row, output_col)
the data format, channels_first or channels_last
A 4d tensor with shape: (batch_size, filters, new_rows, new_cols) if data_format='channels_first' or 4D tensor with shape: (batch_size, new_rows, new_cols, filters) if data_format='channels_last'.
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.