recursiveUtils.lua:44: expecting nested tensors or tables. Got nil and nil instead

[gpfvic]

运行th train.lua, 使用的是dgk_lost_conv的results目录下数据

总是报如下错误：

Dataset stats:
Vocabulary size: 24872
Examples: 66332
dgk ending

-- Epoch 1 / 30

/home/admin/tools/distro/install/bin/luajit: ...ools/distro/install/share/lua/5.1/rnn/recursiveUtils.lua:44: expecting nested tensors or tables. Got nil and nil instead
stack traceback:
[C]: in function 'error'
...ools/distro/install/share/lua/5.1/rnn/recursiveUtils.lua:44: in function 'recursiveCopy'
./seq2seq.lua:58: in function 'backwardConnect'
./seq2seq.lua:78: in function 'train'
train.lua:90: in main chunk
[C]: in function 'dofile'
...ols/distro/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x004064f0

[erwin00776]

--[[ Backward coupling: Copy decoder gradients to encoder LSTM ]]--
function Seq2Seq:backwardConnect()
if (self.encoderLSTM.userNextGradCell ~= nil) then
self.encoderLSTM.userNextGradCell =
nn.rnn.recursiveCopy(self.encoderLSTM.userNextGradCell, self.decoderLSTM.userGradPrevCell)
end
if (self.encoderLSTM.gradPrevOutput ~= nil) then
self.encoderLSTM.gradPrevOutput =
nn.rnn.recursiveCopy(self.encoderLSTM.gradPrevOutput, self.decoderLSTM.userGradPrevOutput)
end
end

I fixed like this.

[wilddylan]

Holy crap @erwin00776 ! You're a magician! Nice work and thx

[andy8023heart]

thx @erwin00776 !