ValueError: bad axis2 argument to swapaxes

[sara-kassani]

In line 74 (gt_im = np.swapaxes(self.train_im, 0, 1)[4]) at extract_patches.py I will get the following error.
ValueError: bad axis2 argument to swapaxes.

[Issam28]

Are you using Brats2017 datasets ? which numpy version do you use?

[sara-kassani]

I'm using brats 2017 and my numpy version is 1.14.2.

[Issam28]

it's really weird in my local machine i can't reproduce the error can you give more details ?

[ritwik12]

I am also getting the same error

[sara-kassani]

I've run the code on google colab and the problem was solved. I guess the error caused because of memory error.

[Issam28]

yes it's probably because of memory when you transform large numpy arrays into np.float you'll quickly run out of memory , i've done this project on a machine that has 64 GO of RAM and i've tested it on google colab which has 13GO of ram and it worked

[ritwik12]

@sara-kassani I have never used colab. Can you guide me how to use this project for colab? if it's not a long procedure for you to explain.

[sara-kassani]

@ritwik12 It's not easy to work with google colab. I've also worked with http://floydhub.com/ and http://paperspace.com/. I recommend you paperspace.

[ritwik12]

@sara-kassani ohk, thanks a lot for your help.

[agungfathur]

i try the program, but still error in line 74 with same error. i already try it on google colabs. any solutions?

[Issam28]

@agungfathur check the filepath of the dataset

[TigabuYaya]

Please could you provide me the output?

[TigabuYaya]

In line 74 (gt_im = np.swapaxes(self.train_im, 0, 1)[4]) at extract_patches.py I will get the following error.
ValueError: bad axis2 argument to swapaxes.

This is because your file paths, @ line 216 and 217 ( path_HGG = glob('Brats2017/Brats17TrainingData/HGG/')
path_LGG = glob('Brats2017/Brats17TrainingData/LGG/')), are not correctly specified.

[takrouni]

Good morning,
Please, i need urgently the Brats2017 dataset
Thank you.

[TigabuYaya]

Good morning,
Please, i need urgently the Brats2017 dataset
Thank you.

your email, please.

[takrouni]

Hello, Same problem :( Le mer. 5 déc. 2018 à 7:02 PM, Mickind <notifications@github.com> a écrit :

…

Hello everyone, How can I find the Brats2017 dataset? I think, without it, I can not execute extract_patches.py. @TigabuYaya <https://github.com/TigabuYaya> Could you please kindly pass me by email? My e-mail: ***@***.*** — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#2 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AO_bWOBzR42xpVzVNXoUJRS2efQhn8L6ks5u2ApQgaJpZM4TJHBb> .

[Issam28]

for everyone's asking for BraTS 2017 or BraTS 2018 datasets you can request them via this website : https://ipp.cbica.upenn.edu/

[Wonkun-Chen]

Hello, is there anybody could send me a BraTS2017 datasets please? when I wrote an email to cbica ask for the datasets, they say they dont provide this datasets, only the latest one, so im here search for it. who can send it to my email(15689432890@163.com)? please!!!

[TigabuYaya]

I hv z dataset

…

On Sun, Apr 12, 2020, 15:13 Jukern-Steven ***@***.***> wrote: Hello, is there anybody could send me a BraTS2017 datasets please? when I wrote an email to cbica ask for the datasets, they say they dont provide this datasets, only the latest one, so im here search for it. who can send it to my ***@***.***)? please!!! — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#2 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AHX2H6CON4O3YPOQHSVP7CDRMGV5NANCNFSM4EZEOBNQ> .

[cqlouis]

In line 74 (gt_im = np.swapaxes(self.train_im, 0, 1)[4]) at extract_patches.py I will get the following error.
ValueError: bad axis2 argument to swapaxes.

This is because your file paths, @ line 216 and 217 ( path_HGG = glob('Brats2017/Brats17TrainingData/HGG/') path_LGG = glob('Brats2017/Brats17TrainingData/LGG/')), are not correctly specified.

yes!
I met the same problem, after I changed the path to absolute path , it worked!