Experimenting with Seeds

Learn how GAN can generate different images using a combination of seed values.

So far, we’ve thought of the seed that feeds the generator as just a random number. After a GAN has been trained, that seed can gain some interesting properties. Let’s see for ourselves.

Approach 1: Choosing values between   seed  1  \;seed\; 1\; and   seed  2\;seed\;2

Imagine two different seeds, seed  1seed\;1 and seed  2seed\;2. We can generate images from both of these seeds. Now imagine a seed that was half way between seed  1seed\;1 and seed  2seed\;2. What would the generated image look like? In fact, what would images look like for seeds at regular intervals between seed  1seed\;1 and seed  2seed\;2?

Get hands-on with 1400+ tech skills courses.