Problem of running the test script

[YantianZha]

Hello,

I downloaded the data with the .sh downloading script you provided, I also got an nps weights file after training. When I ran the testing command I got the following error:
Traceback (most recent call last):
File "/home/research/DL/VIN/pytorch-value-iteration-networks/test.py", line 158, in
main(config)
File "/home/research/DL/VIN/pytorch-value-iteration-networks/test.py", line 85, in main
_, predictions = vin(X_in, S1_in, S2_in, config)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 357, in call
result = self.forward(*input, **kwargs)
File "/home/research/DL/VIN/pytorch-value-iteration-networks/model.py", line 64, in forward
return logits, self.sm(logits)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 352, in call
for hook in self._forward_pre_hooks.values():
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 398, in getattr
type(self).name, name))
AttributeError: 'Softmax' object has no attribute '_forward_pre_hooks'

Thanks for helping!

[kentsommer]

Hi @YantianZha

I'm aware of this bug and will fix it as soon as I can set aside some time (likely not until this weekend).

It is due to softmax no longer providing a default dimension. Due to how I am currently saving the weights, fixing this will require retraining. Along with the fix to this bug, I will also be updating how the weights are saved so that this type of issue can be fixed more quickly in the future.

[YantianZha]

Hi Kent, Thanks! Best, Yantian

…

________________________________ From: Kent Sommer <notifications@github.com> Sent: Tuesday, April 10, 2018 5:26 PM To: kentsommer/pytorch-value-iteration-networks Cc: YantianZha; Mention Subject: Re: [kentsommer/pytorch-value-iteration-networks] Problem of running the test script (#4) Hi @YantianZha<https://github.com/YantianZha> I'm aware of this bug and will fix it as soon as I can set aside some time (likely not until this weekend). It is due to softmax no longer providing a default dimension. Due to how I am currently saving the weights, fixing this will require retraining. Along with the fix to this bug, I will also be updating how the weights are saved so that this type of issue can be fixed more quickly in the future. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<#4 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AImZ71AnyBseB3vvt0WmZTxtNXTGgRs5ks5tnU21gaJpZM4TPL4j>.

[kentsommer]

Fixed with 15fefd5