search

ginobilinie / medSynthesis

medical image synthesis with GAN framework based on tensorflow (we also have a better version in pytorch: https://github.com/ginobilinie/medSynthesisV1)
MIT License
72 stars 24 forks source link

why doesn't the 3D model contain a discriminator? #9

Closed NatalieZou closed 2 years ago

NatalieZou commented 5 years ago

I read the 3D code and didn't find a discriminator in it. So isn't the 3D model an adversarial network?

ginobilinie commented 5 years ago

Check it:

https://github.com/ginobilinie/medSynthesis/tree/master/3dganversion

NatalieZou commented 5 years ago

Thanks a lot!

NatalieZou commented 5 years ago

Check it:

https://github.com/ginobilinie/medSynthesis/tree/master/3dganversion

I read this code carefully, the discriminator seems to be useless, there is no optimizer of discriminator

ginobilinie commented 5 years ago

I'm now very busy for hunting for jobs. I cannot check it very carefully for you. After this period, I can find my previous codes (it was two years ago) and upload the correct one. For now you can use this one (this one has been tested by many others and it also contains 2d and 3d version):

https://github.com/ginobilinie/medSynthesisV1

ginobilinie commented 5 years ago

@NatalieZou You can also check this repository again, I update it: https://github.com/ginobilinie/medSynthesis/tree/master/3dganversion

NatalieZou commented 5 years ago

@ginobilinie Thank you so much!