Awesome

L2M-GAN

Unofficial PyTorch implementation of L2M-GAN.

Steps

Download the wing.ckpt and put it in ./archive/models/.
Download the CelebA-HQ dataset from here.
Use the script ./bin/split_celeba.py to generate the dataset split, rename the generated folder to celeba_hq_smiling and then put it in ./archive/.
Make the shell script executable: chmod u+x ./scripts/train.sh
Execute the shell script: ./scripts/train.sh

TODOs

Implement the models.
Implement the loss functions.
Make it runnable.
Start the experiments.

Results

Experiment #1: Attribute Smiling

Final best FID: 16.93 (100k iterations) default_setting_smiling_test_100000

The first row is the origin images, the second row is the smiling one and the third row is the non-smiling one.

Experiment #2: Attribute Gender

Final best FID: 32.83 (100k iterations) default_setting_gender_test_100000

The first row is the origin images, the second row is the female one and the third row is the male one.