DeepPrime2Sec icon indicating copy to clipboard operation
DeepPrime2Sec copied to clipboard

where the X_test_408.npy?

Open fciasth opened this issue 6 years ago • 13 comments

Can't find the test set, please open the test set, thank you for your research.

fciasth avatar Oct 13 '19 02:10 fciasth

Same issue here. Where can the file X_test_408.npy be downloaded from. Thanks in advance

redna11 avatar Dec 13 '19 18:12 redna11

Hi there, sorry for the late response. Please find it here: http://deepbio.info/proteomics/datasets/deepprime2sec/train_files.tar.gz. The training file contains every feature concatinated. Please refer to the README and if you had further questions please let me know.

ehsanasgari avatar Dec 13 '19 21:12 ehsanasgari

Hello, this is the training file which contains X_train_408.npy, but how about the test file: X_test_408.npy ? thanks

redna11 avatar Dec 13 '19 21:12 redna11

You could find it here: https://github.com/ehsanasgari/DeepPrime2Sec/tree/master/datasets

ehsanasgari avatar Dec 13 '19 21:12 ehsanasgari

Ah yes I was just wondering if you had the npy file ready, but nevermind I will build it from the text file. Thanks for your assistance. Have to say it again the code in the repo is super easy to read and well structured. well done!

redna11 avatar Dec 13 '19 21:12 redna11

You're very welcome. The npy file is also there: "test_mat_Y.npy". Are you looking for something else?

ehsanasgari avatar Dec 13 '19 21:12 ehsanasgari

I was expecting the file: X_test_408.npy to be found next to X_train_408.npy I can see that it is possible to build it from scratch by reading the text file, but it would really save a couple of hours to all users of the repo if the prebuilt "X_test_408.npy" was included (or available as a download). Cheers

redna11 avatar Dec 13 '19 21:12 redna11

I thought this is also the same as X_test_408. But will check this later and if was not the same will upload the correct file.

ehsanasgari avatar Dec 13 '19 22:12 ehsanasgari

appreciate it, thanks

redna11 avatar Dec 13 '19 22:12 redna11

Hello, I have tried to reconstruct the missing X_test_408.npy file from test.txt, but the results when training the algo do not match the expected. It only gets about 56% test accuracy, versus expected 70%. I assume there is an issue in the way I am building X_test_408.npy . Any chance to provide that file? Its shape should be (514, 700,408)

Without it results cannot be replicated properly.

Thanks!

redna11 avatar Dec 18 '19 10:12 redna11

Hello @redna11 How have you reconstructed the X_test? I'm trying to replicate it too.

Thanks in advance.

D-hash avatar Jan 15 '20 19:01 D-hash

please share X_test_408.npy file It is missing.

afaquealam avatar Nov 10 '22 08:11 afaquealam

Hello @redna11 How have you reconstructed the X_test? I'm trying to replicate it too.

afaquealam avatar Nov 10 '22 08:11 afaquealam