Regarding line 58 in preprocess .py

Kyfafyd / MirrorGAN

Reproduction of the paper MirrorGAN: Learning Text-to-image Generation by Redescription

MIT License

25 stars 4 forks source link

Regarding line 58 in preprocess .py #10

Open saba56 opened 2 years ago

saba56 commented 2 years ago

Could you please let me know what is the purpose of line for c in filelist2: if c == 'Muscular' or c == 'Circulatory' or c == 'Dental_Tooth': continue ff = os.listdir('data/health/CUB_200_2011/images/' + c)

Kyfafyd commented 2 years ago

I have tried to apply MirrorGAN to a medical image generation task. So this is specified for that task, you can generate for your own by modifying this.

saba56 commented 2 years ago

Thanks for the reply....But when I generate the class_info.pickle and the filenames .pickle for birds dataset using this code, the files do not resemble the original filenemes.pickle and class-info.pickle that are there in the Birds dataset.....More importantly class_info.pickle has entire different format.....

Kyfafyd commented 2 years ago

That is just a reference, I think this part is not difficult, you can further try it on your own.

saba56 commented 2 years ago

Yes but i am not able to make out the things from class_info.pickle....What do below parameters indicate

(lp0 cnumpy.core.multiarray scalar p1 (cnumpy dtype p2 (S'i8' p3 I0 I1 tp4 Rp5 (I3 S'<' p6 NNNI-1 I-1 I0 tp7 bS'\x02\x00\x00\x00\x00\x00\x00\x00' p8 tp9