nn.upsampling about pvnet HOT 14 CLOSED

from pvnet.

Use nn.functional.interpolate instead.
warnings.warn("nn.Upsampling is deprecated. Use nn.functional.interpolate instead.")
Segmentation fault (core dumped)

from pvnet.

so can I modifie the upsampling in the model_repository.py

from pvnet.

Yes

from pvnet.

what value should I take for the scale_factor(0.5 ?), and I think you can rewrite the network.

from pvnet.

I has tried, but the problem of Segmentation fault is not solved

from pvnet.

In pytorch v0.4.1, it is just a warning and won't cause errors.
For this case, I suppose that you cannot run other pytorch codes either.

from pvnet.

And why there existes a segmentation fault ? I use gdb to debug, the problem is __gnu_cxx, but I do not know how to make it?

from pvnet.

It is a pytorch problem, and I don't know why.

from pvnet.

I also encountered the same problem and also used the GDB debugging tool. The error is located in a layer called _UP, which crashes when the forward function is executed.

[The system environment is centos7.2, the gcc version is 4.8.5, the python version is 3.6.8, and the torch version is 0.4.1.]

from pvnet.

The problem means you cannot run 'nn.upsampling()', which is exactly a pytorch problem.

from pvnet.

I also encountered the same problem and also used the GDB debugging tool. The error is located in a layer called _UP, which crashes when the forward function is executed.

[The system environment is centos7.2, the gcc version is 4.8.5, the python version is 3.6.8, and the torch version is 0.4.1.]

Solved: upgrade gcc version to 5.4.0.

from pvnet.

@DHNicoles I encountered the same problem -- segmentation fault. And my GPU is RTX, so I have to use pytorch 1.x according to the author. Can you give me more details about how did you solve this problem? My gcc version is 5.4.0.

from pvnet.

@zeal-github It's better to check again if you have a strict configuration according to the author's requirements.

from pvnet.