Git Product home page Git Product logo

drcn's Introduction

This is a pytorch implementation of the model Deep Reconstruction-Classification Network for Unsupervised Domain Adapation (DRCN).

Environment

  • Pytorch 0.4.0
  • Python 2.7

Structure

DRCN

Usage

  • put the mnist and svhn data in the entries in dataset, respectively
  • if there is no Grayscale transform in your torchvision, please replace your functional.py and transforms.py with provided files in extra
  • run python main.py for training
  • the trained model will be saved in model, and recontructed images saved in recovery_image
  • In our implementation, no denoising include

Result

real svhn

Real and Recovered SVHN images

drcn's People

Contributors

fungtion 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 avatar avatar

Watchers

avatar avatar avatar avatar

Forkers

twistedmove dupanfei1 dengwanxia1991 gufeicang 459548764 tangzixia zhonglingyuxiuyyx aaron2bin chenjiehu wuzhan11 hariknguyen

drcn's Issues

RuntimeError: input and target shapes do not match

Sorry，I have a problem about input and target shapes do not match when I rerun your code.
Could you give me some advices?
Traceback (most recent call last): File "main.py", line 137, in <module> err_rec = (1 - m_lambda) * loss_rec(rec_img, inputv_img) File "/home/gqwang/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 491, in __call__ result = self.forward(*input, **kwargs) File "/home/gqwang/anaconda2/lib/python2.7/site-packages/torch/nn/modules/loss.py", line 372, in forward return F.mse_loss(input, target, size_average=self.size_average, reduce=self.reduce) File "/home/gqwang/anaconda2/lib/python2.7/site-packages/torch/nn/functional.py", line 1569, in mse_loss input, target, size_average, reduce) File "/home/gqwang/anaconda2/lib/python2.7/site-packages/torch/nn/functional.py", line 1537, in _pointwise_loss return lambd_optimized(input, target, size_average, reduce) RuntimeError: input and target shapes do not match: input [64 x 1024], target [64 x 1 x 32 x 32] at /opt/conda/conda-bld/pytorch_1524577177097/work/aten/src/THCUNN/generic/MSECriterion.cu:15 Exception NameError: "global name 'FileNotFoundError' is not defined" in <bound method _DataLoaderIter.__del__ of <torch.utils.data.dataloader._DataLoaderIter object at 0x7f35aac72b10>> ignored

Some question about your implementation

Whether your implementation is the official code? I try your code and want to get the performance reported in DRCN paper, while the reconstruction part has a negative effect.

the accuracy

Is the accuracy of the code is about 0.72? But there is 0.81 in the paper.

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.