PyTorch implementation of Image-to-Image Translation with Conditional Adversarial Nets (pix2pix)

• Image size: 256x256
• Number of training images: 400
• Number of test images: 106

• Adam optimizer is used. Learning rate = 0.0002, batch size = 1, # of epochs = 200:

GAN losses ( : Generator / : Discriminator)	Generated images (Input / Generated / Target)

• Generated images using test data

  1st column: Input / 2nd column: Generated / 3rd column: Target

• Image size: 256x256
• Number of training images: 2,975
• Number of test images: 500

• Adam optimizer is used. Learning rate = 0.0002, batch size = 1, # of epochs = 200:

GAN losses ( : Generator / : Discriminator)	Generated images (Input / Generated / Target)

• Generated images using test data

  1st column: Input / 2nd column: Generated / 3rd column: Target

• Image is resized to 256x256 image (Original size: 600x600)
• Number of training images: 1,096
• Number of test images: 1,098

• Adam optimizer is used. Learning rate = 0.0002, batch size = 1, # of epochs = 200:

GAN losses ( : Generator / : Discriminator)	Generated images (Input / Generated / Target)

• Generated images using test data

  1st column: Input / 2nd column: Generated / 3rd column: Target

• Image size: 256x256
• Number of training images: 49,825
• Number of test images: 200

• Adam optimizer is used. Learning rate = 0.0002, batch size = 4, # of epochs = 15:

GAN losses ( : Generator / : Discriminator)	Generated images (Input / Generated / Target)

• Generated images using test data

  1st column: Input / 2nd column: Generated / 3rd column: Target

• Image size: 256x256
• Number of training images: 138,567
• Number of test images: 200

• Adam optimizer is used. Learning rate = 0.0002, batch size = 4, # of epochs = 15:

GAN losses ( : Generator / : Discriminator)	Generated images (Input / Generated / Target)

• Generated images using test data

  1st column: Input / 2nd column: Generated / 3rd column: Target

1. https://github.com/mrzhu-cool/pix2pix-pytorch
2. https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
3. https://github.com/znxlwm/pytorch-pix2pix
4. https://affinelayer.com/pix2pix/