Class: DNN::Layers::LSTM_Dense

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

Instance Method Summary collapse

Constructor Details

#initialize(rnn) ⇒ LSTM_Dense

Returns a new instance of LSTM_Dense.



210
211
212
213
214
215
216
217
 
# File 'lib/dnn/core/rnn_layers.rb', line 210

def initialize(rnn)
  @rnn = rnn
  @tanh = Tanh.new
  @g_tanh = Tanh.new
  @forget_sigmoid = Sigmoid.new
  @in_sigmoid = Sigmoid.new
  @out_sigmoid = Sigmoid.new
end

Instance Method Details

#backward(dh2, dc2) ⇒ Object 



237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
 
# File 'lib/dnn/core/rnn_layers.rb', line 237

def backward(dh2, dc2)
  dh2_tmp = @tanh_c2 * dh2
  dc2_tmp = @tanh.backward(@out * dh2) + dc2

  dout = @out_sigmoid.backward(dh2_tmp)
  din = @in_sigmoid.backward(dc2_tmp * @g)
  dg = @g_tanh.backward(dc2_tmp * @in)
  dforget = @forget_sigmoid.backward(dc2_tmp * @c)

  da = Xumo::SFloat.hstack([dforget, dg, din, dout])

  @rnn.grads[:weight] += @x.transpose.dot(da)
  @rnn.grads[:weight2] += @h.transpose.dot(da)
  if @rnn.l1_lambda > 0
    @rnn.grads[:weight] += dlasso
    @rnn.grads[:weight2] += dlasso2
  elsif @rnn.l2_lambda > 0
    @rnn.grads[:weight] += dridge
    @rnn.grads[:weight2] += dridge2
  end
  @rnn.grads[:bias] += da.sum(0)
  dx = da.dot(@rnn.params[:weight].transpose)
  dh = da.dot(@rnn.params[:weight2].transpose)
  dc = dc2_tmp * @forget
  [dx, dh, dc]
end

#forward(x, h, c) ⇒ Object 



219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
 
# File 'lib/dnn/core/rnn_layers.rb', line 219

def forward(x, h, c)
  @x = x
  @h = h
  @c = c
  num_nodes = h.shape[1]
  a = x.dot(@rnn.params[:weight]) + h.dot(@rnn.params[:weight2]) + @rnn.params[:bias]

  @forget = @forget_sigmoid.forward(a[true, 0...num_nodes])
  @g = @g_tanh.forward(a[true, num_nodes...(num_nodes * 2)])
  @in = @in_sigmoid.forward(a[true, (num_nodes * 2)...(num_nodes * 3)])
  @out = @out_sigmoid.forward(a[true, (num_nodes * 3)..-1])

  c2 = @forget * c + @g * @in
  @tanh_c2 = @tanh.forward(c2)
  h2 = @out * @tanh_c2
  [h2, c2]
end