search

eriklindernoren / Keras-GAN

Keras implementations of Generative Adversarial Networks.
MIT License
9.19k stars 3.14k forks source link

ACGAN: Difference multiplication and concatenation of embedding and noise #259

Open ghost opened 2 years ago

ghost commented 2 years ago

Hi, I noticed that you multiply the class embedding vector and the noise vector to generate the input of the model. In other ACGAN implementations I noticed that the noise and class embeddings vector were concatenated.

Should one method be preferred over the other or do they have the same result?

Thank you in advance!