xxlya / fed_abide Goto Github PK
View Code? Open in Web Editor NEWimpelmentation of https://arxiv.org/pdf/2001.05647.pdf
fed_abide's People
Contributors
Stargazers
Watchers
fed_abide's Issues
Data Preprocessing
Firstly, thank for the excellent work you have contributed to the privacy protection clinical set.
But I don't have the following file after running run.sh. What should I do
Question about the experiment results
Hello, i have a question about the experiment result. After i run the federated code, i get the following result.
But i find it is different from the result of paper.
Especially, the result of the USM and UCLA is so weird! I hope you can give me some advices, thanks!
when run the code, i just use the cpu.
Warning when run truncation.py
Hello, thank you for sharing your work. After I run the preprocess script truncation.py, I saw som warnings from console:
truncation.py:23: RuntimeWarning: divide by zero encountered in arctanh
fisher = np.arctanh(correlation_matrix)
Does it matter?
Thank you :)
My environment:
# packages in environment at /home/wangshu/miniconda3/envs/abide:
#
# Name Version Build Channel
_libgcc_mutex 0.1 main defaults
_openmp_mutex 4.5 1_gnu defaults
blas 1.0 openblas defaults
ca-certificates 2021.7.5 h06a4308_1 defaults
certifi 2021.5.30 py36h06a4308_0 defaults
cffi 1.14.6 py36h400218f_0 defaults
charset-normalizer 2.0.4 pypi_0 pypi
crc32c 2.2.post0 pypi_0 pypi
cudatoolkit 10.0.130 0 defaults
cycler 0.10.0 py36_0 defaults
dbus 1.13.18 hb2f20db_0 defaults
deepdish 0.3.6 pypi_0 pypi
expat 2.4.1 h2531618_2 defaults
fontconfig 2.13.1 h6c09931_0 defaults
freetype 2.10.4 h5ab3b9f_0 defaults
glib 2.69.0 h5202010_0 defaults
gst-plugins-base 1.14.0 h8213a91_2 defaults
gstreamer 1.14.0 h28cd5cc_2 defaults
icu 58.2 he6710b0_3 defaults
idna 3.2 pypi_0 pypi
intel-openmp 2021.3.0 h06a4308_3350 defaults
joblib 1.0.1 pypi_0 pypi
jpeg 9b h024ee3a_2 defaults
kiwisolver 1.3.1 py36h2531618_0 defaults
lcms2 2.12 h3be6417_0 defaults
ld_impl_linux-64 2.35.1 h7274673_9 defaults
libffi 3.3 he6710b0_2 defaults
libgcc-ng 9.3.0 h5101ec6_17 defaults
libgfortran-ng 7.5.0 ha8ba4b0_17 defaults
libgfortran4 7.5.0 ha8ba4b0_17 defaults
libgomp 9.3.0 h5101ec6_17 defaults
libopenblas 0.3.13 h4367d64_0 defaults
libpng 1.6.37 hbc83047_0 defaults
libstdcxx-ng 9.3.0 hd4cf53a_17 defaults
libtiff 4.2.0 h85742a9_0 defaults
libuuid 1.0.3 h1bed415_2 defaults
libwebp-base 1.2.0 h27cfd23_0 defaults
libxcb 1.14 h7b6447c_0 defaults
libxml2 2.9.12 h03d6c58_0 defaults
lz4-c 1.9.3 h295c915_1 defaults
matplotlib 3.3.4 py36h06a4308_0 defaults
matplotlib-base 3.3.4 py36h62a2d02_0 defaults
mkl 2021.3.0 h06a4308_520 defaults
ncurses 6.2 he6710b0_1 defaults
nibabel 3.2.1 pypi_0 pypi
nilearn 0.6.2 pypi_0 pypi
ninja 1.10.2 hff7bd54_1 defaults
numexpr 2.7.3 pypi_0 pypi
numpy 1.17.0 py36h99e49ec_0 defaults
numpy-base 1.17.0 py36h2f8d375_0 defaults
olefile 0.46 py36_0 defaults
openjpeg 2.3.0 h05c96fa_1 defaults
openssl 1.1.1k h27cfd23_0 defaults
packaging 21.0 pypi_0 pypi
pandas 1.1.5 pypi_0 pypi
pcre 8.45 h295c915_0 defaults
pillow 8.3.1 py36h2c7a002_0 defaults
pip 21.2.2 py36h06a4308_0 defaults
protobuf 3.17.3 pypi_0 pypi
pycparser 2.20 py_2 defaults
pyparsing 2.4.7 pyhd3eb1b0_0 defaults
pyqt 5.9.2 py36h05f1152_2 defaults
python 3.6.13 h12debd9_1 defaults
python-dateutil 2.8.2 pyhd3eb1b0_0 defaults
pytorch 1.1.0 py3.6_cuda10.0.130_cudnn7.5.1_0 pytorch
pytz 2021.1 pypi_0 pypi
qt 5.9.7 h5867ecd_1 defaults
readline 8.1 h27cfd23_0 defaults
requests 2.26.0 pypi_0 pypi
scikit-learn 0.24.2 pypi_0 pypi
scipy 1.5.4 pypi_0 pypi
setuptools 52.0.0 py36h06a4308_0 defaults
sip 4.19.8 py36hf484d3e_0 defaults
six 1.16.0 pyhd3eb1b0_0 defaults
sklearn 0.0 pypi_0 pypi
sqlite 3.36.0 hc218d9a_0 defaults
tables 3.6.1 pypi_0 pypi
tensorboardx 2.4 pypi_0 pypi
threadpoolctl 2.2.0 pypi_0 pypi
tk 8.6.10 hbc83047_0 defaults
torchvision 0.3.0 py36_cu10.0.130_1 pytorch
tornado 6.1 py36h27cfd23_0 defaults
urllib3 1.26.6 pypi_0 pypi
wheel 0.36.2 pyhd3eb1b0_0 defaults
xz 5.2.5 h7b6447c_0 defaults
zlib 1.2.11 h7b6447c_3 defaults
zstd 1.4.9 haebb681_0 defaults
Error in backpropagation for federated_align
Hi,
Thank you so much for sharing the code of this work!
I've encountered a problem when running the file "federated_align". I think the problem is related to the backpropagation with retain_graph=True of the adversarial loss in lines 312-316.
Traceback (most recent call last): in
lossG.backward(retain_graph=True)
File "/home/amelia/anaconda3/envs/py36pytorch1/lib/python3.6/site-packages/torch/tensor.py", line 221, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/amelia/anaconda3/envs/py36pytorch1/lib/python3.6/site-packages/torch/autograd/init.py", line 132, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [4, 1]], which is output 0 of TBackward, is at version 2; expected version 1 instead.
Any ideas about why this is happening and how could I fix it? Thanks again!
data preprocess
How to generate the following data? I don't seem to find how to generate these data in the data processing code.
Question on federated unsupervised domain adaptation
Firstly, thank for the excellent work you have contributed to the privacy protection clinical set.
But, I have some question to ask so that I can know more clear about the federated learning.
I want to know that in federated unsupervised domain adaptation setting, we have two different classifier(local and global), the local classifier is trained using one site data and the global classifier is updated based on the four different local classifiers. For example, the NYU site data have been splited into train and test set, the global classifier will contain some information of NYU site(for the using NYU train set to train the local classifier and the global classifier is updated based on local classifier). If it is a semi-supervised learning and not a unsupervised learning setting.
I want to know if I have understand the federated learning correctly, so I wish to get your reply sincerely
Finally, thanks for your excellent work on the federated domain adaptation one more time!
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.