Kevin Zhu
Kevin Zhu
z is just noise. You can simply add: ` z = np.random.normal(loc=0.0, scale=1.0, size=[flags.batch_size, flags.z_dim]).astype(np.float32)` before `Gen.save_weights('{}/Gen.npz'.format(flags.checkpoint_dir), format='npz')`
Create a new folder called "data" and put you image into that folder. Then, run train.py. Generated new images are saved in samples folder.