To install
wget https://repo.anaconda.com/archive/Anaconda3-2019.10-Linux-x86_64.sh
export PATH="/home/hgupta/anaconda3/bin:$PATH"
conda create --name cryoem --file ./cryoemfinal/install.txt
conda activate cryoem
pip install "pillow<7"
cryogan's Introduction
cryogan's People
cryogan's Issues
Error in astra package with data shape
I am trying to run CryoGAN to reproduce results published in your paper.
I encountered a problem. We successfully set up the conda environment, but when we try running the code with any of the supplied configuration files, we encounter a problem.
After fixing several misslinked paths I finally managed to get it running but after the training process starts I get the error below. I did set up the environment with the same packages, but also tried other versions of astra toolbox.
By running this command:
python main_Clean.py Configs/train_Betagal.cfg
I get this error:
...
Starting the training process ...
Lr decreases every 1.0 epochs
starting Training
Gaussian Blurring everything with sigma 2.0
Varphigenerator data size 101
Traceback (most recent call last):
File "main_Clean.py", line 51, in <module>
pro_gan.train(dataset=dataset, num_workers=1)
File "/home/bohakc/cryogan/CryoGAN-Feng/CryoGAN_Clean.py", line 119, in train
dis_lossIter, wass_lossIter, real_samples = self.optimize_discriminator(images)
File "/home/bohakc/cryogan/CryoGAN-Feng/CryoGAN_Clean.py", line 261, in optimize_discriminator
fake_samples, _, _, _, _ = self.gen(real_samples, GaussianSigma=self.args.GaussianSigma, ratio=self.ratio)
File "/home/bohakc/cryogan/cryoem-env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/bohakc/cryogan/CryoGAN-Feng/Networks_Clean.py", line 39, in forward
ratio=ratio)
File "/home/bohakc/cryogan/cryoem-env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/bohakc/cryogan/CryoGAN-Feng/Generators_Clean.py", line 46, in forward
proj, projClean = self.Projection(X, self.CurrentAngles)
File "/home/bohakc/cryogan/CryoGAN-Feng/Generators_Clean.py", line 82, in Projection
proj = Projection(X[0], self.args.RawProjectionSize, vectors.cpu())
File "/home/bohakc/cryogan/CryoGAN-Feng/Functions/FunctionsGenerator.py", line 40, in Projection
proj = Project.apply(X, RawProjectionSize, vectors)
File "/home/bohakc/cryogan/CryoGAN-Feng/Functions/FunctionsGenerator.py", line 305, in forward
vol_id = astra.data3d.link('-vol', vol_geom, vol_link)
File "/home/bohakc/cryogan/cryoem-env/lib/python3.6/site-packages/astra/data3d.py", line 64, in link
return d.create(datatype,geometry,data,True)
File "astra/data3d_c.pyx", line 94, in astra.data3d_c.create
ValueError: The dimensions of the data do not match those specified in the geometry: (2, 384, 192) != (2, 192, 384)
Do you have any idea what to do to fix this?
Un resolved references in FunctionsGenerator
Hello,
I was trying to reproduce the results of your wonderful paper. However, there are few functions in the FunctionsGenerator file that don't exist in the project repository. These are _doPlots, CTFGeneratorSpatial, UnSymmetryFunction, Support.SymCreator, and Support.SymUncreator _. Is there any chance that you explain what are these? It seems some part of the project is missing. Thanks a lot. @harshit-gupta-cor
Usage Guide
Hi,
Can you provide a guide on how to use the tool?
Regards,
Raj
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.