L2 2-D normalization layer for SSD300/512 architecture.

L2 2-D normalization layer for SSD300/512 architecture described in

Value

output tensor with the same shape as the input.

Details

Wei Liu, Andrew Rabinovich, and Alexander C. Berg. ParseNet: Looking Wider to See Better.

available here:

    \code{https://arxiv.org/abs/1506.04579}

Usage

layer <- L2NormalizationLayer2D$new( scale )

layer$call( x, mask = NULL )
layer$build( input_shape )
layer$compute_output_shape( input_shape )

Arguments

layer

A process object.

scale

feature scale. Default = 20

x

mask

input_shape

Details

$initialize instantiates a new class.

$build

$call main body.

$compute_output_shape computes the output shape.

Author

Tustison NJ

Examples

x = L2NormalizationLayer2D$new()
#> Error in py_discover_config(required_module, use_environment): Python specified in RETICULATE_PYTHON (/Users/ntustison/anaconda3/envs/antsx/bin/python3) does not exist
if (FALSE) {
x$build(input_shape = c(20, 20, 20, 3))
}