Problem about stitching/branch_train.py.

[SpiritBear000]

At [https://github.com/penincillin/DREAM/blob/7bea01e5b108546a2b3a809ad17cf478607c9db5/src/stitching/branch_train.py#L52]

when i run this code, i get this error:

Traceback (most recent call last):
File "/media/lab210/Work/WH_HOME/SubjectDownload/Project/Face-reid/[ DREAM-Face ]/DREAM/src/stitching/branch_train.py", line 134, in
main()
File "/media/lab210/Work/WH_HOME/SubjectDownload/Project/Face-reid/[ DREAM-Face ]/DREAM/src/stitching/branch_train.py", line 52, in main
losses.update(loss.data[0], loss.size(0))
RuntimeError: dimension specified as 0 but tensor has no dimensions

when i replace 'loss' to 'loss.size(0)'. the code can run. is it a bug when you design your code?

[tataganesh95]

Could be because of this - hunkim/PyTorchZeroToAll#24

[SpiritBear000]

Could be because of this - hunkim/PyTorchZeroToAll#24

thank you! There is another question to ask.

In

DREAM/src/stitching/branch_train.py

Line 51 in 7bea01e

loss = criterion(output, batch_target_feat)

The output of MSEloss is a scalar，why a scalar have '.size()'?

And i am confused about the function 'AverageMeter' which is in (

DREAM/src/stitching/branch_train.py

Line 118 in 7bea01e

def update(self, val, n=1):

)
what's the meaning of 'n' in AverageMeter.update?

[penincillin]

Thanks for asking,
This issue might be caused by the version of Pytorch.
This code is developed with Pytorch 0.3 and might be not compatible with Pytorch 0.4.
As for the bug you report, I believe it is not a tough one, you could try to solve by yourself :)

[clhne]

@SpiritBear000
Just modify the code:
losses.update(loss.data[0], loss.size(0))
to
losses.update(loss.data, loss)
Then run it.