Code Monkey home page Code Monkey logo

pytorch_wbn's People

Contributors

mancinimassimiliano avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar

Forkers

redhat12345 tinyloop wjx2 wangkanger xychen9459 min9kwak marcociccone zhao1f semi-supervised-paper cll308

pytorch_wbn's Issues

WBN2d is not callable

Dear author, thanks a lot for your codes! However, when I call WBN2d in a network to replace nn.Batchnorm2d, during forward process x= WBN2d(x,w), it always reports "forward only takes two inputs, but 3 were given." When I track it down, I found out the problem seems that the class WBN2d can't be called. Any idea what may be the reason?

Backward illegal memory access

Hi, I'm trying to use your layer, but I encountered a strange issue. I correctly included it in my network, it correctly calculates the weighted normalization in forward, but when I try to call a backward it gives the following error:

Traceback (most recent call last):
  File "train.py", line 455, in <module>
    t = Trainer(parser.parse_args())
  File "train.py", line 60, in __init__
    self.train()
  File "train.py", line 71, in train
    train_loss_d1, train_loss_d2 = self.trainOneEpoch(i)
  File "train.py", line 312, in trainOneEpoch
    loss_value.backward(retain_graph=True)
  File "/localhome/c-fpizzati/anaconda3/lib/python3.6/site-packages/torch/tensor.py", line 93, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph)
  File "/localhome/c-fpizzati/anaconda3/lib/python3.6/site-packages/torch/autograd/__init__.py", line 90, in backward
    allow_unreachable=True)  # allow_unreachable flag
RuntimeError: cuda runtime error (77) : an illegal memory access was encountered at /opt/conda/conda-bld/pytorch_1532579245307/work/aten/src/THC/generated/../generic/THCTensorMathPointwise.cu:266

Do you have any idea? I'm on torch 0.4.1 cuda 9.2.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.