tf.keras.backend.local_conv2d

View source on GitHub

Apply 2D conv with un-shared weights.

tf.keras.backend.local_conv2d(
    inputs, kernel, kernel_size, strides, output_shape, data_format=None
)

Arguments:

Returns:

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'.