Class: DNN::Layers::UnPool2D

Inherits:
Layer
  • Object
show all
Includes:
Conv2DUtils, LayerNode
Defined in:
lib/dnn/core/layers/cnn_layers.rb

Instance Attribute Summary collapse

Attributes inherited from Layer

#input_shape, #output_shape

Instance Method Summary collapse

Methods included from Conv2DUtils

calc_conv2d_out_size, calc_conv2d_padding_size, calc_conv2d_transpose_out_size, calc_conv2d_transpose_padding_size, col2im, col2im_cpu, col2im_gpu, im2col, im2col_cpu, im2col_gpu, zero_padding, zero_padding_bwd

Methods included from LayerNode

#forward

Methods inherited from Layer

#<<, #built?, #call, call, #clean, #forward, from_hash

Constructor Details

#initialize(unpool_size) ⇒ UnPool2D

Returns a new instance of UnPool2D.

Parameters:

  • unpool_size (Array | Integer) —

    Unpooling size. unpooling size is of the form [height, width].



442
443
444
445
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 442

def initialize(unpool_size)
  super()
  @unpool_size = unpool_size.is_a?(Integer) ? [unpool_size, unpool_size] : unpool_size
end

Instance Attribute Details

#unpool_size ⇒ Object (readonly)

Returns the value of attribute unpool_size.



439
440
441
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 439

def unpool_size
  @unpool_size
end

Instance Method Details

#backward_node(dy) ⇒ Object 



472
473
474
475
476
477
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 472

def backward_node(dy)
  in_size = @input_shape[0..1]
  col = im2col(dy, *in_size, *@unpool_size, @unpool_size)
  col = col.reshape(dy.shape[0] * in_size.reduce(:*), @unpool_size.reduce(:*), dy.shape[3])
  col.sum(1).reshape(dy.shape[0], *in_size, dy.shape[3])
end

#build(input_shape) ⇒ Object 



447
448
449
450
451
452
453
454
455
456
457
458
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 447

def build(input_shape)
  unless input_shape.length == 3
    raise DNNShapeError, "Input shape is #{input_shape}. But input shape must be 3 dimensional."
  end
  prev_h, prev_w = input_shape[0..1]
  unpool_h, unpool_w = @unpool_size
  out_h = prev_h * unpool_h
  out_w = prev_w * unpool_w
  @out_size = [out_h, out_w]
  @num_channel = input_shape[2]
  super
end

#compute_output_shape ⇒ Object 



479
480
481
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 479

def compute_output_shape
  [*@out_size, @num_channel]
end

#forward_node(x) ⇒ Object 



460
461
462
463
464
465
466
467
468
469
470
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 460

def forward_node(x)
  @x_shape = x.shape
  unpool_h, unpool_w = @unpool_size
  x2 = Xumo::SFloat.zeros(x.shape[0], x.shape[1], unpool_h, x.shape[2], unpool_w, @num_channel)
  unpool_h.times do |i|
    unpool_w.times do |j|
      x2[true, true, i, true, j, true] = x
    end
  end
  x2.reshape(x.shape[0], *@out_size, x.shape[3])
end

#load_hash(hash) ⇒ Object 



487
488
489
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 487

def load_hash(hash)
  initialize(hash[:unpool_size])
end

#to_hash ⇒ Object 



483
484
485
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 483

def to_hash
  super(unpool_size: @unpool_size)
end