Awesome
Conditional GAN
Conditional Generative Adversarial Networks for anime generation (AnimeGAN).
<br /> Training results dump every 500 min-batch in 25 epoch(26000th min-batch) for the following tags
- blue hair blue eyes <br />
- gray hair green eyes <br />
- green hair red eyes <br />
- orange hair brown eyes <br />
- blonde hair gray eyes <br />
- pink hair aqua eyes <br />
Sample training data
<br />
Environment
python3 <br /> tensorflow 1.0 <br /> scipy <br />
Model structure
Data
source link <br /> google drive link
Usage
- Download hw3 data from data link, place the MLDS_HW3_dataset/ in the same directory and unzip the face.zip in MLDS_HW3_dataset/
- Replace the tags in MLDS_HW3_dataset/sample_testing_text.txt to the right format.
- Start training !
Train
First time use, you need to do the preprocessing
$ python3 main.py --prepro 1
If you already have done the preprocessing
$ python3 main.py --prepro 0
Model
- dcgan structure
- use one hot encoding for condition tags
Test
This code will automatically dump the results for the tags specified in MLDS_HW3_dataset/sample_testing_text.txt every <em>dump_every</em> batches to the test_img/ folder. <br />
Testing tags format
1,<Color> hair <Color> eyes
2,<Color> hair <Color> eyes
3,<Color> hair <Color> eyes
4,<Color> hair <Color> eyes
.
.
.
- Possible colors for eyes
['<UNK>', 'yellow', 'gray', 'blue', 'brown', 'red', 'green', 'purple', 'orange',
'black', 'aqua', 'pink', 'bicolored']
- Possible colors for hair
['<UNK>', 'gray', 'blue', 'brown', 'red', 'blonde', 'green', 'purple', 'orange',
'black', 'aqua', 'pink', 'white']