Class: DNN::Layers::GRUDense

Inherits:
Object
  • Object
show all
Defined in:
lib/dnn/core/rnn_layers.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(weight, recurrent_weight, bias) ⇒ GRUDense 



361
362
363
364
365
366
367
368
369
 
# File 'lib/dnn/core/rnn_layers.rb', line 361

def initialize(weight, recurrent_weight, bias)
  @weight = weight
  @recurrent_weight = recurrent_weight
  @bias = bias
  @update_sigmoid = Layers::Sigmoid.new
  @reset_sigmoid = Layers::Sigmoid.new
  @tanh = Layers::Tanh.new
  @trainable = true
end

Instance Attribute Details

#trainable ⇒ Object

Returns the value of attribute trainable.



359
360
361
 
# File 'lib/dnn/core/rnn_layers.rb', line 359

def trainable
  @trainable
end

Instance Method Details

#backward(dh2) ⇒ Object 



394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
 
# File 'lib/dnn/core/rnn_layers.rb', line 394

def backward(dh2)
  dtanh_h = @tanh.backward(dh2 * (1 - @update))
  dh = dh2 * @update

  if @trainable
    dweight_h = @x.transpose.dot(dtanh_h)
    dweight2_h = (@h * @reset).transpose.dot(dtanh_h)
    dbias_h = dtanh_h.sum(0) if @bias
  end
  dx = dtanh_h.dot(@weight_h.transpose)
  dh += dtanh_h.dot(@weight2_h.transpose) * @reset

  dreset = @reset_sigmoid.backward(dtanh_h.dot(@weight2_h.transpose) * @h)
  dupdate = @update_sigmoid.backward(dh2 * @h - dh2 * @tanh_h)
  da = Xumo::SFloat.hstack([dupdate, dreset])
  if @trainable
    dweight_a = @x.transpose.dot(da)
    dweight2_a = @h.transpose.dot(da)
    dbias_a = da.sum(0) if @bias
  end
  dx += da.dot(@weight_a.transpose)
  dh += da.dot(@weight2_a.transpose)

  if @trainable
    @weight.grad += Xumo::SFloat.hstack([dweight_a, dweight_h])
    @recurrent_weight.grad += Xumo::SFloat.hstack([dweight2_a, dweight2_h])
    @bias.grad += Xumo::SFloat.hstack([dbias_a, dbias_h]) if @bias
  end
  [dx, dh]
end

#forward(x, h) ⇒ Object 



371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
 
# File 'lib/dnn/core/rnn_layers.rb', line 371

def forward(x, h)
  @x = x
  @h = h
  num_nodes = h.shape[1]
  @weight_a = @weight.data[true, 0...(num_nodes * 2)]
  @weight2_a = @recurrent_weight.data[true, 0...(num_nodes * 2)]
  a = x.dot(@weight_a) + h.dot(@weight2_a)
  a += @bias.data[0...(num_nodes * 2)] if @bias
  @update = @update_sigmoid.forward(a[true, 0...num_nodes])
  @reset = @reset_sigmoid.forward(a[true, num_nodes..-1])

  @weight_h = @weight.data[true, (num_nodes * 2)..-1]
  @weight2_h = @recurrent_weight.data[true, (num_nodes * 2)..-1]
  @tanh_h = if @bias
              bias_h = @bias.data[(num_nodes * 2)..-1]
              @tanh.forward(x.dot(@weight_h) + (h * @reset).dot(@weight2_h) + bias_h)
            else
              @tanh.forward(x.dot(@weight_h) + (h * @reset).dot(@weight2_h))
            end
  h2 = (1 - @update) * @tanh_h + @update * h
  h2
end