Closed YYan-97 closed 3 years ago
Hi @YYan-97 ,
Those are some errors I got when using the generators, they happen because of some weird problems with the numpy random generator and a race condition which normally should be fine when not using multiprocessing so I am a bit surprised. Which version of the code are you on?
Also, on Monday afternoon I will dedicate my time to fixing the scripts used in this paper since too many of them are outdated (maybe in a separate repo, I will let you know).
You could try fixing this script yourself but I think it would be a bit too much for you.
Hi @zaccharieramzi ,
I just realized I was using an older version of the scripts. I just tried the latest version, the errors disappeared and it could run successfully. I guess it has something to do with the callback TQDMCallback. In other scripts like pdnet and unet, I modified the TQDMCallback to TQDMProgressBar directly and ran the scripts successfully, so I did not even realize this problem. In kikinet_sep I was not sure how to modify that so I just left it there.
I realized this is a very minor issue. Thank you for your help!
Glad to know, so I guess we can close this for now and I will try to still find the will to put this in order
Closing this since we now have reproducible scripts thanks to #113
Hi there,
I'm trying to reproduce the results of the paper Ramzi, Z.; Ciuciu, P.; Starck, J.-L. Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets. Appl. Sci. 2020, 10, 1816. and adapt the models to the reconstruction of other types of MR images. According to the checkpoints provided, it seems the training of the kikinet used the script fastmri_recon/training_scripts/single_coil/kikinet_sep_approach_af4.py. So right now I'm trying to run this training script, but I encounter some problems.
I modified the scripts a little bit by setting the use_multiprocsessing as false, disabling the GPU, setting n_epochs as 1 and setting chkpt_cback to save the checkpoints only at the last epoch. I keep getting this warning:
Could someone explain what is going wrong here and how should I modify the script?
The whole script is presented as follows
And here is what I get