Timeline for How does the generator in GAN's work?
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 10, 2020 at 9:24 | history | edited | Djib2011 | CC BY-SA 4.0 |
Elaborated on input as suggested by comment
|
| Dec 10, 2020 at 1:46 | comment | added | nbro | This answer does not really explain why the input to the generator should be a noise/random vector. It may be worth adding a few lines that attempt to address this from a theoretical point of view. | |
| Jan 22, 2020 at 10:46 | vote | accept | Shir K | ||
| Jan 18, 2020 at 17:19 | comment | added | Djib2011 | You are thinking of it the wrong way. The generator doesn't search through all possible combinations of values so that it can produce an exact replica of the input images. It just tries to confuse the Discriminator. How does it do that? By mimicking the "patterns" that the Discriminator sees in real images when trying to distinguish them from fake ones. | |
| Jan 18, 2020 at 17:17 | comment | added | Djib2011 | If your dataset has let's say RGB images (i.e. $3$ channels) with a resolution of $256 \times 256$, the Generator should take a vector of random numbers as its input and output a tensor of $256 \times 256 \times 3$ (its output should have the same shape as the input images). | |
| Jan 18, 2020 at 17:15 | comment | added | Shir K | @Djib2012 What do you mean by same shape? I will try to simplfy my question - if the fake image x* is this marix: [1,2,3], in the worse case it would take 10^3~ of iterations of generator-discriminator until I recieve the required x*. Since real images represented by larger matrix, it would be many many more than I described. Why wouldnt you insert as an input an example of real image x? | |
| Jan 18, 2020 at 1:12 | comment | added | Djib2011 | It's a neural network whose output has the same shape as the input. In a lot of cases it resembles an inverted discriminator (which is a typical binary classifier). | |
| Jan 17, 2020 at 18:05 | comment | added | personjerry | But you haven't explained how the generator works, as in the question. I.e. what kind of algorithm does the generator use to create a convincing dataset, and how does the "learning" work for that algorithm? | |
| Jan 17, 2020 at 10:47 | history | answered | Djib2011 | CC BY-SA 4.0 |