Closed wushilian closed 6 years ago
Uses Keras image preprocessing. Look at keras documentation but this is pretty simple. Expects each dataset to be in a directory containing directories of images corresponding to label.
So in order to use a custom dataset what code file do i have to modify? Or it is just to have the right directory structure?
Hey, you shouldn't have to modify the code. Synthesized images in one dir, refined in another. Make sure directories are named correctly. See keras image processing docs for more info.
Another question, Once the network is trained, how do i generate refined images?
@dagoPA Did you solve this problem?how to get refined images?
@wushilian I haven't yet Because i think this project only takes a random small set of data to inference and instead of saving it only saves the weights and the plot
@dagoPA It seems like that.
@wushilian i think in the code i stead of predict batch we need a loop that iterates predicting each image in target directory
@dagoPA that's all right.And I think cycle GAN and simGAN are very similar,so now I use cycleGAN to Converte synthetic data into real data
@wushilian I saw you forked that project, im new to github but i hope i can know your email
@dagoPA I guess you have saw my email,so I deleted it.
I want to use the simgan to train other dataset,so what format does the data need?