Giter VIP home page Giter VIP logo

mm-gan's People

Contributors

jianjuly avatar trane293 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

Forkers

jianjuly

mm-gan's Issues

Running conda env create -f environment.yml, many packages fail from ResolvePackageNotFound. The environment.yml was exported from a machine where the environment was working fine.

ResolvePackageNotFound:

  • scipy==1.1.0=py35hfa4b5c9_1
  • qt==5.6.3=h39df351_1
  • pyqt==5.6.0=py35h8210e8a_7
  • mkl_random==1.0.1=py35h4414c95_1
  • glib==2.56.2=hd408876_0
  • h5py==2.8.0=py35h989c5e5_3
  • jpeg==9b=h024ee3a_2
  • hdf5==1.10.2=hba1933b_1
  • freetype==2.9.1=h8a8886c_1
  • gst-plugins-base==1.14.0=hbbd80ab_1
  • libuuid==1.0.3=h1bed415_2
  • numpy-base==1.15.2=py35h81de0dd_0
  • scikit-image==0.14.0=py35hfc679d8_1
  • cudnn==7.1.2=cuda9.0_0
  • nccl==1.3.5=cuda9.0_0
  • numpy==1.15.2=py35h1d66e8a_0
  • pcre==8.42=h439df22_0
  • pytorch==0.4.1=py35ha74772b_0
  • dbus==1.13.2=h714fa37_1
  • sip==4.18.1=py35hfc679d8_0
  • libgcc-ng==8.2.0=hdf63c60_1
  • ninja==1.8.2=py35h6bb024c_1
  • tornado==5.1.1=py35h470a237_0
  • libgfortran-ng==7.3.0=hdf63c60_0
  • ncurses==6.1=hf484d3e_0
  • cudatoolkit==9.0=h13b8566_0
  • fontconfig==2.13.0=h9420a91_0
  • matplotlib==2.2.3=py35h8e2386c_0
  • icu==58.2=h9c2bf20_1
  • libpng==1.6.35=hbc83047_0
  • libtiff==4.0.9=he85c1e1_2
  • pywavelets==1.0.1=py35h7eb728f_0
  • libstdcxx-ng==8.2.0=hdf63c60_1
  • libxml2==2.9.8=h26e45fe_1
  • mkl_fft==1.0.6=py35h7dd41cf_0
  • sqlite==3.25.3=h7b6447c_0
  • libffi==3.2.1=hd88cf55_4
  • libxcb==1.13=h1bed415_1
  • python==3.5.5=hc3d631a_4
  • expat==2.2.6=he6710b0_0
  • libedit==3.1.20170329=h6b74fdf_2
  • kiwisolver==1.0.1=py35hf484d3e_0
  • xz==5.2.4=h14c3975_4
  • zlib==1.2.11=ha838bed_2
  • readline==7.0=h7b6447c_5
  • tk==8.6.8=hbc83047_0
  • cffi==1.11.5=py35he75722e_1
  • pillow==5.2.0=py35heded4f4_0
  • gstreamer==1.14.0=hb453b48_1
  • openssl==1.0.2p=h470a237_1

Pretrained model weight

I follow the readme.md command step, use ./mmgan_hgg.sh training Brats2018 data, but network can't converge.
loss_d_real/fake and gan_adv_loss have been declining. I don't know if this is correct.
Cloud you share me with your pretrained model weight?

Output Doubts

Good morning,
I would like to know if the output files will be NIfTI as BRATS dataset, i.e., since the input files are in three dimensions if the output will have the same dimensions.
Regards,
André Ferreira.

Vague instructions

The instructions in "Open modules/configfile.py and change the following paths to match your folder structure:" are a little vague.

What folder structure? The zip files do not contain files like: 'BRATS2018_Unprocessed.h5'

It will be really helpful if you can add some screenshots and show how you set it up on your computer so that users can have some reference.

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.