Chainer implementation for Image-to-Image Translation Using Conditional Adversarial Networks, it's transplanted from pix2pix.

Sign up, Log in & Download gtFine_trainvaltest.zip & leftImg8bit_trainvaltest.zip from cityscapes

    python split_data_sets.py --root [Image Folder] --list [List Folder]  

Note: Run python split_data_sets.py -h for more details.

    python combine_A_and_B.py --list [List Path] --save_dir [Save Folder]

	ls train > train.txt
	ls val > val.txt
	ls test > test.txt

Note: Run commands above in folder containing train, val & test subfolder

	python train.py

Note: Run python train.py -h for more options.

	python test.py

Note: Run python test.py -h for more options.

U-net

PatchGAN, FOV is determined by n_layers.

Code borrows heavily from Chainer: DCGAN.