adler-j / learned_gradient_tomography Goto Github PK

Bonjour,

Is there any cpu implementation of the code ?
I read in your paper that you have used the ’astra gpu’ backend.

Regards

Hi, I'm currently using your learned gradient tomography in a 3D case.
I would like to use a poisson noise instead of a white noise

So in your generate_data function I replace:

data = operator(phantom)
noisy_data = data + odl.phantom.white_noise(operator.range) * np.mean(np.abs(data)) * 0.05
fbp = pseudoinverse(noisy_data)

By:

data = operator(phantom)
noise = np.random.poisson(0.05,size=operator.range.shape)
noisy_data = data + noise
fbp = pseudoinverse(noisy_data)

But I don't get a good result, the image is only noisy in some places

After some researches I noticed that it was due to the following code:

# Ensure operator has fixed operator norm for scale invariance
opnorm = odl.power_method_opnorm(operator)
operator = (1 / opnorm) * operator
pseudoinverse = pseudoinverse * opnorm

But if I remove this part of code the network does not learn anymore.

I would like to know if there is a clean way to apply a good poisson noise on data.
Thank you in advance for your assistance with this.

Hi, I am learning your paper and code.
When I run partially_learned_gradient_descent_head.py, I have this error message ;
TypeError: 'skimage' backend only supports 2d parallel geometries
Google don't have enough information, and how to settle it? Thanks.

Hi, I am learning your paper and code.

I installed ODL correctly according to the commands ：
'$ conda install -c odlgroup odl matplotlib pytest scikit-image spyder’,
but when I run these program, I have this error message:
space = odl.uniform_discr([-1, -1], [1, 1], [100, 100])
AttributeError: module 'odl' has no attribute 'uniform_discr'.

I'm sure that I have install discr. How can I solve it?
I run these codes in pycharm.
This is the specific information of some packages I installed.
python 3.6.13
odl 0.7.0
numpy 1.19.5
By the way, the URL https://github.com/adler-j/odl/archive/tensorflow_support.zip is no longer accessible.

According to odlgroup/odl#1092

Hey Jonas,

I was trying to run code: "Partially_learned_gradient_descent.py" in this repository but I have encountered a dilemma as follow.

In order to utilize GPU for the computation of forward and backward projection in ODL, it is mandatory for us to install "Astra-toolbox". However, installing "Astra-toolbox" will downgrade package "numpy" to version 1.12. If we import tensorflow (version 1.13.1) to python in this situation, the following error message will occur:

ModuleNotFoundError: No module named 'numpy.core._multiarray_umath'
ImportError: numpy.core.multiarray failed to import

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "", line 968, in _find_and_load
SystemError: <class '_frozen_importlib._ModuleLockManager'> returned a result with an error set
ImportError: numpy.core._multiarray_umath failed to import
ImportError: numpy.core.umath failed to import

I have tried to upgrade "numpy" (for instance, to version 1.16) after installing "astra-toolbox", but then ODL will complain there is no available back-end for Ray-Transform.

Have you met this problem before? If so, could you please tell me how could I solve it? Thanks for your attention, I am looking forward to hear back from you.

Cheers,
Bo