cat(): argument 'tensors' (position 1) must be tuple of Tensors, not generator

[caoxu915683474]

SPM_toolkit/DecAtt/main_quora.py

Line 56 in 3e2cb35

left_sents = torch.cat((dict[word].view(1, -1) for word in lsent))

cat(): argument 'tensors' (position 1) must be tuple of Tensors, not generator

can I fix this bug use this line?

torch.cat(tuple([dict[word].view(1, -1) for word in lsent]))

[caoxu915683474]

torch.cat([dict[word].view(1, -1) for word in lsent])

is this also ok ?

[lanwuwei]

Hi caoxu, I tried your second answer in other code:
https://github.com/lanwuwei/Subword-PWIM/blob/6e9ef11fa404c4ea6e350f8e75f7d1055869d8d9/model.py#L436
In my PyTorch version 0.4.0, both are OK. You can modify the code based on your version.

[caoxu915683474]

@lanwuwei
Thanks for your help, I find my pytorch version is not 0.4.0.