Wrong Decoder RNN Architecture

[Ar-Kareem]

In the decoder an LSTM is used

Pytorch-Sketch-RNN/sketch_rnn.py

Lines 151 to 157 in 5c3e213

	class DecoderRNN(nn.Module):
	def __init__(self):
	super(DecoderRNN, self).__init__()
	# to init hidden and cell from z:
	self.fc_hc = nn.Linear(hp.Nz, 2*hp.dec_hidden_size)
	# unidirectional lstm:
	self.lstm = nn.LSTM(hp.Nz+5, hp.dec_hidden_size, dropout=hp.dropout)

While in the original paper, the description of the architecture at page 6 states that

For the decoder RNN, we use HyperLSTM, as this type of RNN cell excels at sequence generation tasks

Referring to a very different implementation of an LSTM that can generate different weights for itself for every element in a sequence. The model is defined in this paper as well as implementation details defined in the Appendix Sections 2.2 and 2.3