PQ-NET icon indicating copy to clipboard operation
PQ-NET copied to clipboard

some questions about results.

Open laodouza opened this issue 4 years ago • 7 comments

Dear Dr.Wu, I am a student of UESTC and I'm very interesetd about your work. Thanks for your code and data. I get the results of auoencoder of your work. It looks very well. But when I use the part of GAN, I meet some problems. The generated results is not look like an entire shape. And do you konw what happen?The dataset I used is chair. Looking forward to you reply. --------------- by a sincerely reader

laodouza avatar Dec 30 '20 09:12 laodouza

I don’t know why, I can’t upload pictures for now, but it seems that there is only one part, such as the part where the armrest and the seat are connected.

laodouza avatar Dec 30 '20 09:12 laodouza

微信图片_20201230173405

laodouza avatar Dec 30 '20 09:12 laodouza

Did you use the pretrained model? How do you get the above voxel outputs?

ChrisWu1997 avatar Dec 30 '20 10:12 ChrisWu1997

with h5py.File(save_path, 'r') as fp: voxel = fp['voxel'][:] np.save('0095.npy',voxel)

i use this code to save the voxel.

laodouza avatar Dec 30 '20 11:12 laodouza

and I did not use the pretrained model. I used the code released to train.

laodouza avatar Dec 30 '20 11:12 laodouza

If the autoencoder works fine but the GAN doesn't work, then it means the problem comes from the latent GAN training. I'm not able to tell what the exact problem is without detailed informations.

Can you try the pretrained model first and see if that works? To make sure the current problem comes from the latent GAN training, rather than other parts.

ChrisWu1997 avatar Dec 30 '20 13:12 ChrisWu1997

ok, I will try. Thank you for your prompt reply .

laodouza avatar Dec 30 '20 13:12 laodouza