Chintan2108 / Cloud-Removal-in-Satellite-Images-using-Conditional-Generative-Adversarial-Networks

Removing cloud cover in Sentinel-2 satellite images using only optical data and a novel augmented training approach using conditional GANs.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Explore more single-scene augmented training approaches

Chintan2108 opened this issue · comments

  • Currently the network is being trained on a single scene which has been rotated at 0, 90, -90 and 180 degrees.
  • Explore more augmentation strategies such as contrast augmentation, skew augmentation, flip augmentation
  • Try and train with various augmented data and record the best results from amongst all