Unofficial PyTorch implementation of L2M-GAN.
./archive/models/
../bin/split_celeba.py
to generate the dataset split, rename the generated folder to celeba_hq_smiling
./archive/
.chmod u+x ./scripts/train.sh
./scripts/train.sh
Final best FID: 16.93 (100k iterations)
The first row is the origin images, the second row is the smiling one and the third row is the non-smiling one.
Final best FID: 32.83 (100k iterations)
The first row is the origin images, the second row is the female one and the third row is the male one.